Markdown + RSS Parser for .NET Standard, MarkdownTextBlock Style Improvements, Syntax Highlighting

Microsoft.Toolkit.Parsers/Core/IParser.cs

@@ -0,0 +1,31 @@
+// ******************************************************************
+// Copyright (c) Microsoft. All rights reserved.
+// This code is licensed under the MIT License (MIT).
+// THE CODE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
+// INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+// IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+// TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH
+// THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
+// ******************************************************************
+
+using System.Collections.Generic;
+
+namespace Microsoft.Toolkit.Parsers
+{
+    /// <summary>
+    /// Parser interface.
+    /// </summary>
+    /// <typeparam name="T">Type to parse into.</typeparam>
+    public interface IParser<out T>
+        where T : SchemaBase
+    {
+        /// <summary>
+        /// Parse method which all classes must implement.
+        /// </summary>
+        /// <param name="data">Data to parse.</param>
+        /// <returns>Strong typed parsed data.</returns>
+        IEnumerable<T> Parse(string data);
+    }
+}

Microsoft.Toolkit.Uwp.Services/Rss/RssParser.cs → Microsoft.Toolkit.Parsers/Core/ParseHelpers.cs

@@ -10,42 +10,37 @@
 // THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
 // ******************************************************************
 
-using System.Collections.Generic;
-using System.Xml.Linq;
-
-namespace Microsoft.Toolkit.Uwp.Services.Rss
+namespace Microsoft.Toolkit.Parsers.Core
 {
     /// <summary>
-    /// RssParser.
+    /// This class offers helpers for Parsing.
     /// </summary>
-    internal class RssParser : IParser<RssSchema>
+    public static class ParseHelpers
     {
         /// <summary>
-        /// Parse string to strong type.
+        /// Determines if a Markdown string is blank or comprised entirely of whitespace characters.
         /// </summary>
-        /// <param name="data">Input string.</param>
-        /// <returns>Strong type.</returns>
-        public IEnumerable<RssSchema> Parse(string data)
+        /// <returns>true if blank or white space</returns>
+        public static bool IsMarkdownBlankOrWhiteSpace(string str)
         {
-            if (string.IsNullOrEmpty(data))
+            for (int i = 0; i < str.Length; i++)
             {
-                return null;
+                if (!IsMarkdownWhiteSpace(str[i]))
+                {
+                    return false;
+                }
             }
 
-            var doc = XDocument.Parse(data);
-            var type = BaseRssParser.GetFeedType(doc);
-
-            BaseRssParser rssParser;
-            if (type == RssType.Rss)
-            {
-                rssParser = new Rss2Parser();
-            }
-            else
-            {
-                rssParser = new AtomParser();
-            }
+            return true;
+        }
 
-            return rssParser.LoadFeed(doc);
+        /// <summary>
+        /// Determines if a character is a Markdown whitespace character.
+        /// </summary>
+        /// <returns>true if is white space</returns>
+        public static bool IsMarkdownWhiteSpace(char c)
+        {
+            return c == ' ' || c == '\t' || c == '\r' || c == '\n';
         }
     }
-}
+}

Microsoft.Toolkit.Uwp.UI.Controls/MarkdownTextBlock/Display/ILinkRegister.cs → Microsoft.Toolkit.Parsers/Core/SchemaBase.cs

@@ -10,15 +10,16 @@
 // THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
 // ******************************************************************
 
-using Windows.UI.Xaml.Documents;
-
-namespace Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Display
+namespace Microsoft.Toolkit.Parsers
 {
     /// <summary>
-    /// An internal interface used to handle links in the markdown.
+    /// Strong typed schema base class.
     /// </summary>
-    internal interface ILinkRegister
+    public abstract class SchemaBase
     {
-        void RegisterNewHyperLink(Hyperlink newHyperlink, string linkUrl);
+        /// <summary>
+        /// Gets or sets identifier for strong typed record.
+        /// </summary>
+        public string InternalID { get; set; }
     }
-}
+}

Microsoft.Toolkit.Parsers/Core/StringValueAttribute.cs

@@ -0,0 +1,38 @@
+// ******************************************************************
+// Copyright (c) Microsoft. All rights reserved.
+// This code is licensed under the MIT License (MIT).
+// THE CODE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
+// INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+// IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+// TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH
+// THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
+// ******************************************************************
+
+using System;
+
+namespace Microsoft.Toolkit.Parsers.Core
+{
+    /// <summary>
+    /// The StringValue attribute is used as a helper to decorate enum values with string representations.
+    /// </summary>
+    [AttributeUsage(AttributeTargets.Field)]
+    public sealed class StringValueAttribute : Attribute
+    {
+        /// <summary>
+        /// Initializes a new instance of the <see cref="StringValueAttribute"/> class.
+        /// Constructor accepting string value.
+        /// </summary>
+        /// <param name="value">String value</param>
+        public StringValueAttribute(string value)
+        {
+            Value = value;
+        }
+
+        /// <summary>
+        /// Gets property for string value.
+        /// </summary>
+        public string Value { get; }
+    }
+}

Microsoft.Toolkit.Uwp.UI.Controls/MarkdownTextBlock/Parse/Blocks/CodeBlock.cs → Microsoft.Toolkit.Parsers/Markdown/Blocks/CodeBlock.cs

@@ -11,15 +11,16 @@
 // ******************************************************************
 
 using System.Text;
-using Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Helpers;
+using Microsoft.Toolkit.Parsers.Markdown.Enums;
+using Microsoft.Toolkit.Parsers.Markdown.Helpers;
 
-namespace Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Parse
+namespace Microsoft.Toolkit.Parsers.Markdown.Blocks
 {
     /// <summary>
     /// Represents a block of text that is displayed in a fixed-width font.  Inline elements and
     /// escape sequences are ignored inside the code block.
     /// </summary>
-    internal class CodeBlock : MarkdownBlock
+    public class CodeBlock : MarkdownBlock
     {
         /// <summary>
         /// Initializes a new instance of the <see cref="CodeBlock"/> class.
@@ -34,6 +35,13 @@ public CodeBlock()
         /// </summary>
         public string Text { get; set; }
 
+        /// <summary>
+        /// Gets or sets the Language specified in prefix, e.g. ```c# (Github Style Parsing).<para/>
+        /// This does not guarantee that the Code Block has a language, or no language, some valid code might not have been prefixed, and this will still return null. <para/>
+        /// To ensure all Code is Highlighted (If desired), you might have to determine the language from the provided string, such as looking for key words.
+        /// </summary>
+        public string CodeLanguage { get; set; }
+
         /// <summary>
         /// Parses a code block.
         /// </summary>
@@ -48,6 +56,7 @@ internal static CodeBlock Parse(string markdown, int start, int maxEnd, int quot
             StringBuilder code = null;
             actualEnd = start;
             bool insideCodeBlock = false;
+            string codeLanguage = string.Empty;
 
             /*
                 Two options here:
@@ -84,6 +93,15 @@ Or the code block starts and ends with ```
                             actualEnd = lineInfo.StartOfNextLine;
                             break;
                         }
+                        else
+                        {
+                            // Collects the Programming Language from the end of the starting ticks.
+                            while (pos < lineInfo.EndOfLine)
+                            {
+                                codeLanguage += markdown[pos];
+                                pos++;
+                            }
+                        }
                     }
                 }
 
@@ -168,7 +186,11 @@ Or the code block starts and ends with ```
             }
 
             // Blank lines should be trimmed from the start and end.
-            return new CodeBlock() { Text = code.ToString().Trim('\r', '\n') };
+            return new CodeBlock()
+            {
+                Text = code.ToString().Trim('\r', '\n'),
+                CodeLanguage = !string.IsNullOrWhiteSpace(codeLanguage) ? codeLanguage.Trim() : null
+            };
         }
 
         /// <summary>
@@ -180,4 +202,4 @@ public override string ToString()
             return Text;
         }
     }
-}
+}

Microsoft.Toolkit.Uwp.UI.Controls/MarkdownTextBlock/Parse/Blocks/HeaderBlock.cs → Microsoft.Toolkit.Parsers/Markdown/Blocks/HeaderBlock.cs

@@ -12,14 +12,16 @@
 
 using System;
 using System.Collections.Generic;
-using Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Helpers;
+using Microsoft.Toolkit.Parsers.Markdown.Enums;
+using Microsoft.Toolkit.Parsers.Markdown.Helpers;
+using Microsoft.Toolkit.Parsers.Markdown.Inlines;
 
-namespace Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Parse
+namespace Microsoft.Toolkit.Parsers.Markdown.Blocks
 {
     /// <summary>
     /// Represents a heading.
     /// </summary>
-    internal class HeaderBlock : MarkdownBlock
+    public class HeaderBlock : MarkdownBlock
     {
         /// <summary>
         /// Initializes a new instance of the <see cref="HeaderBlock"/> class.
@@ -170,4 +172,4 @@ public override string ToString()
             return string.Join(string.Empty, Inlines);
         }
     }
-}
+}

Microsoft.Toolkit.Uwp.UI.Controls/MarkdownTextBlock/Parse/Blocks/HorizontalRuleBlock.cs → Microsoft.Toolkit.Parsers/Markdown/Blocks/HorizontalRuleBlock.cs

@@ -10,14 +10,15 @@
 // THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
 // ******************************************************************
 
-using Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Helpers;
+using Microsoft.Toolkit.Parsers.Core;
+using Microsoft.Toolkit.Parsers.Markdown.Enums;
 
-namespace Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Parse
+namespace Microsoft.Toolkit.Parsers.Markdown.Blocks
 {
     /// <summary>
     /// Represents a horizontal line.
     /// </summary>
-    internal class HorizontalRuleBlock : MarkdownBlock
+    public class HorizontalRuleBlock : MarkdownBlock
     {
         /// <summary>
         /// Initializes a new instance of the <see cref="HorizontalRuleBlock"/> class.
@@ -60,7 +61,7 @@ internal static HorizontalRuleBlock Parse(string markdown, int start, int end)
                 {
                     break;
                 }
-                else if (!Common.IsWhiteSpace(c))
+                else if (!ParseHelpers.IsMarkdownWhiteSpace(c))
                 {
                     return null;
                 }
@@ -79,4 +80,4 @@ public override string ToString()
             return "---";
         }
     }
-}
+}

Microsoft.Toolkit.Uwp.UI.Controls/MarkdownTextBlock/Parse/Blocks/LinkReferenceBlock.cs → Microsoft.Toolkit.Parsers/Markdown/Blocks/LinkReferenceBlock.cs

@@ -10,14 +10,16 @@
 // THE CODE OR THE USE OR OTHER DEALINGS IN THE CODE.
 // ******************************************************************
 
-using Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Helpers;
+using Microsoft.Toolkit.Parsers.Core;
+using Microsoft.Toolkit.Parsers.Markdown.Enums;
+using Microsoft.Toolkit.Parsers.Markdown.Inlines;
 
-namespace Microsoft.Toolkit.Uwp.UI.Controls.Markdown.Parse
+namespace Microsoft.Toolkit.Parsers.Markdown.Blocks
 {
     /// <summary>
     /// Represents the target of a reference ([ref][]).
     /// </summary>
-    internal class LinkReferenceBlock : MarkdownBlock
+    public class LinkReferenceBlock : MarkdownBlock
     {
         /// <summary>
         /// Initializes a new instance of the <see cref="LinkReferenceBlock"/> class.
@@ -86,7 +88,7 @@ internal static LinkReferenceBlock Parse(string markdown, int start, int end)
 
             // Skip whitespace
             pos++;
-            while (pos < end && Common.IsWhiteSpace(markdown[pos]))
+            while (pos < end && ParseHelpers.IsMarkdownWhiteSpace(markdown[pos]))
             {
                 pos++;
             }
@@ -98,7 +100,7 @@ internal static LinkReferenceBlock Parse(string markdown, int start, int end)
 
             // Extract the URL.
             int urlStart = pos;
-            while (pos < end && !Common.IsWhiteSpace(markdown[pos]))
+            while (pos < end && !ParseHelpers.IsMarkdownWhiteSpace(markdown[pos]))
             {
                 pos++;
             }
@@ -110,7 +112,7 @@ internal static LinkReferenceBlock Parse(string markdown, int start, int end)
 
             // Skip whitespace.
             pos++;
-            while (pos < end && Common.IsWhiteSpace(markdown[pos]))
+            while (pos < end && ParseHelpers.IsMarkdownWhiteSpace(markdown[pos]))
             {
                 pos++;
             }
@@ -125,10 +127,12 @@ internal static LinkReferenceBlock Parse(string markdown, int start, int end)
                     case '(':
                         tooltipEndChar = ')';
                         break;
+
                     case '"':
                     case '\'':
                         tooltipEndChar = markdown[pos];
                         break;
+
                     default:
                         return null;
                 }
@@ -149,7 +153,7 @@ internal static LinkReferenceBlock Parse(string markdown, int start, int end)
 
                 // Check there isn't any trailing text.
                 pos++;
-                while (pos < end && Common.IsWhiteSpace(markdown[pos]))
+                while (pos < end && ParseHelpers.IsMarkdownWhiteSpace(markdown[pos]))
                 {
                     pos++;
                 }
@@ -177,4 +181,4 @@ public override string ToString()
             return string.Format("[{0}]: {1} {2}", Id, Url, Tooltip);
         }
     }
-}
+}