release: version 0.10.0 🚀

HISTORY.md

@@ -4,12 +4,21 @@ Changelog
 
 (unreleased)
 ------------
+- Feat: add support for custom token types and longs, ref: NOISSUE.
+  [Simon Diesenreiter]
+
+
+0.9.3 (2024-12-13)
+------------------
 
 Fix
 ~~~
 - Remove duplicate TokenConverter definition, ref: NOISSUE. [Simon
   Diesenreiter]
 
+Other
+~~~~~
+
 
 0.9.2 (2024-12-13)
 ------------------

TextParser/Data/TokenConverter.cs

@@ -13,7 +13,7 @@ public class TokenConverter
     {
     }
 
-    private List<T> AsGenericCollection<T, U>() where T : ICollection<U>, new()
+    private List<T> AsGenericCollection<T, U>() where T : List<U>, new()
     {
         List<T> returnData = new List<T>();
         foreach (var tokenRow in this.rawTokens)
@@ -25,11 +25,15 @@ public class TokenConverter
                 {
                     throw new Exception("No token was provided, but token was expected!");
                 }
-                IValueToken<U>? valueToken = token as IValueToken<U>;
-                if (valueToken == null)
+
+                if (!token.GetType().IsAssignableTo(typeof(IValueToken<U>)))
                 {
-                    throw new Exception("Provided token is not a ValueToken");
+                    Console.WriteLine(token.GetText());
+                    Type t = token.GetType();
+                    throw new Exception("Provided token is not a ValueToken - type: " + t.ToString());
                 }
+
+                IValueToken<U> valueToken = token as IValueToken<U>;
                 newRow.Add(valueToken.GetValue());
             }
 
@@ -161,7 +165,7 @@ public class TokenConverter
     {
         var newTokenListList = new List<List<IToken>>();
         
-        foreach(var tokenList in rawTokens)
+        foreach(var tokenList in this.rawTokens)
         {
             var newTokenList = new List<IToken>();
             foreach(var token in tokenList)

TextParser/Schema/BlockType.cs

@@ -11,4 +11,6 @@ public enum BlockType
     FixedRepetition = 16,
     GreedyRepetition = 32,
     NonZeroRepetition = 64,
+    Custom = 128,
+    Long = 256,
 }

TextParser/Schema/BuildingBlocks/CustomInputBlock.cs

@@ -0,0 +1,42 @@
+namespace Parsing.Schema.BuildingBlocks;
+
+using Parsing.Tokenization;
+
+class CustomInputBlock<T> : BuildingBlockBase
+{
+
+    private InputType definedInputType;
+    private Func<string, T> wordConverter;
+
+    public CustomInputBlock(InputType definedInputType, Func<string, T> wordConverter)
+    {
+        this.definedInputType = definedInputType;
+        this.wordConverter = wordConverter;
+    }
+
+    public override List<IToken> ParseWord(InputProvider inputs)
+    {
+        return new List<IToken>() { new CustomToken<T>(inputs.YieldWord(), this.definedInputType, this.wordConverter) };
+    }
+
+    public override bool CanParseWord(InputProvider inputs)
+    {
+        string word = string.Empty;
+        using (inputs.GetLookaheadContext())
+        {
+            word = inputs.YieldWord();
+        }
+
+        return this.CanParseWord(word);
+    }
+
+    public override bool CanParseWord(string word)
+    {
+        return true;
+    }
+
+    public override BlockType GetBlockType()
+    {
+        return BlockType.Custom;
+    }
+}

TextParser/Schema/BuildingBlocks/LongBlock.cs

@@ -0,0 +1,35 @@
+namespace Parsing.Schema.BuildingBlocks;
+
+using Parsing.Tokenization;
+
+class LongBlock : BuildingBlockBase
+{
+
+    public LongBlock()
+    {
+    }
+
+    public override List<IToken> ParseWord(InputProvider inputs)
+    {
+        return new List<IToken>() { new LongToken(inputs.YieldWord()) };
+    }
+
+    public override bool CanParseWord(InputProvider inputs)
+    {
+        using (inputs.GetLookaheadContext())
+        {
+            return this.CanParseWord(inputs.YieldWord());
+        }
+    }
+
+    public override bool CanParseWord(string word)
+    {
+        long number = 0;
+        return long.TryParse(word, out number);
+    }
+
+    public override BlockType GetBlockType()
+    {
+        return BlockType.Long;
+    }
+}

TextParser/Schema/BuildingBlocks/StringBlock.cs

@@ -28,6 +28,12 @@ class StringBlock : BuildingBlockBase
     public override bool CanParseWord(string word)
     {
         // Here we need to ensure we are not matching any non-string tokens, since string can match pretty much anything
+        LongBlock longBlock = new LongBlock();
+        if (longBlock.CanParseWord(word))
+        {
+            return false;
+        }
+
         IntegerBlock intBlock = new IntegerBlock();
         if (intBlock.CanParseWord(word))
         {

TextParser/Schema/InputSchemaBuilder.cs

@@ -21,6 +21,9 @@ public class InputSchemaBuilder : RepetitionSchemaBuilder<InputSchemaBuilder, In
             case InputType.Integer:
                 block = new IntegerBlock();
                 break;
+            case InputType.Long:
+                block = new LongBlock();
+                break;
             case InputType.Char:
                 block = new CharBlock();
                 break;
@@ -31,6 +34,21 @@ public class InputSchemaBuilder : RepetitionSchemaBuilder<InputSchemaBuilder, In
         return this;
     }
 
+    public InputSchemaBuilder Expect<T>(InputType type, InputType definedInputType, Func<string, T> wordConverter)
+    {
+        IBuildingBlock block;
+        switch (type)
+        {
+            case InputType.Custom:
+                block = new CustomInputBlock<T>(definedInputType, wordConverter);
+                break;
+            default:
+                throw new Exception("Unrecognized InputType");
+        }
+        schema.AddBuildingBlock(block);
+        return this;
+    }
+
     public InputSchemaBuilder Repeat(int repetitionCount)
     {
         // add another layer of parsing

TextParser/Schema/InputType.cs

@@ -7,4 +7,6 @@ public enum InputType
     String = BlockType.String,
     Fragment = BlockType.Fragment,
     Char = BlockType.Char,
+    Custom = BlockType.Custom,
+    Long = BlockType.Long,
 }

TextParser/Tokenization/CustomToken.cs

@@ -0,0 +1,34 @@
+namespace Parsing.Tokenization;
+
+using Parsing.Schema;
+
+public class CustomToken<T> : IValueToken<T>
+{
+    private string word;
+
+    private InputType definedInputType;
+
+    private Func<string, T> wordConverter;
+
+    public CustomToken(string word, InputType definedInputType, Func<string, T> wordConverter)
+    {
+        this.word = word;
+        this.wordConverter = wordConverter;
+        this.definedInputType = definedInputType;
+    }
+
+    public string GetText()
+    {
+        return word;
+    }
+
+    public T GetValue()
+    {
+        return wordConverter(word);
+    }
+
+    public InputType GetInputType()
+    {
+        return this.definedInputType;
+    }
+}

TextParser/Tokenization/LongToken.cs

@@ -0,0 +1,28 @@
+namespace Parsing.Tokenization;
+
+using Parsing.Schema;
+
+public class LongToken : IValueToken<long>
+{
+    private string word;
+
+    public LongToken(string word)
+    {
+        this.word = word;
+    }
+
+    public string GetText()
+    {
+        return word;
+    }
+
+    public long GetValue()
+    {
+        return long.Parse(word);
+    }
+
+    public InputType GetInputType()
+    {
+        return InputType.Long;
+    }
+}

TextParser/VERSION

@@ -1 +1 @@
-0.9.3
+0.10.0