feat: add two dimensional data walker, refs: NOISSUE

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/DataConversionHelpers.cs

@@ -5,44 +5,32 @@ using Parsing.Tokenization;
 
 public static class DataConversionHelpers
 {
-    public static List<TNewType> ConvertData<TTokenType, TNewType, TOldType>(this List<IToken> tokenList, Func<TOldType, TNewType> converter) where TTokenType : IValueToken<TOldType>
+    public static List<TNewType> ConvertData<TNewType, TOldType>(this List<TOldType> valueList, Func<TOldType, TNewType> converter)
     {
         var newList = new List<TNewType>();
-        foreach (var token in tokenList)
+        foreach (var value in valueList)
         {
-            var typedToken = token as IValueToken<TOldType>;
-            if (typedToken == null)
-            {
-                throw new Exception("Invalid Token type encountered during value conversion");
-            }
-
-            newList.Add(converter(typedToken.GetValue()));
+            newList.Add(converter(value));
         }
         return newList;
     }
 
-    public static List<TNewType> ConvertData<TTokenType, TNewType, TOldType>(this List<IToken> tokenList, Func<TOldType, List<TNewType>> converter) where TTokenType : IValueToken<TOldType>
+    public static List<TNewType> ConvertData<TNewType, TOldType>(this List<TOldType> valueList, Func<TOldType, List<TNewType>> converter)
     {
         var newList = new List<TNewType>();
-        foreach (var token in tokenList)
+        foreach (var value in valueList)
         {
-            var typedToken = token as IValueToken<TOldType>;
-            if (typedToken == null)
-            {
-                throw new Exception("Invalid Token type encountered during value conversion");
-            }
-
-            newList.AddRange(converter(typedToken.GetValue()));
+            newList.AddRange(converter(value));
         }
         return newList;
     }
 
-    public static List<List<TNewType>> ConvertData<TTokenType, TNewType, TOldType>(this List<List<IToken>> tokenListList, Func<TOldType, TNewType> converter) where TTokenType : IValueToken<TOldType>
+    public static List<List<TNewType>> ConvertData<TNewType, TOldType>(this List<List<TOldType>> valueListList, Func<TOldType, TNewType> converter)
     {
         var newListList = new List<List<TNewType>>();
-        foreach (var tokenList in tokenListList)
+        foreach (var valueList in valueListList)
         {
-            newListList.Add(tokenList.ConvertData<TTokenType, TNewType, TOldType>(converter));
+            newListList.Add(valueList.ConvertData<TNewType, TOldType>(converter));
         }
         return newListList;
     }

TextParser/Data/DataManipulationHelpers.cs

@@ -21,7 +21,7 @@ public static class DataManipulationHelpers
         return reducer(data);
     }
 
-    public static List<TNewType> TransformData<TType, TNewType>(this List<TType> data, Func<TType, TNewType> transformer)
+    public static List<TNewType> TransformData<TType, TNewType>(this IEnumerable<TType> data, Func<TType, TNewType> transformer)
     {
         var newList = new List<TNewType>();
         foreach (TType dataItem in data)
@@ -31,7 +31,7 @@ public static class DataManipulationHelpers
         return newList;
     }
 
-    public static List<TNewType> TransformData<TType, TNewType>(this List<List<TType>> data, Func<List<TType>, TNewType> transformer)
+    public static List<TNewType> TransformData<TType, TNewType>(this IEnumerable<IEnumerable<TType>> data, Func<List<TType>, TNewType> transformer)
     {
         var newList = new List<TNewType>();
         foreach (List<TType> dataItemList in data)
@@ -40,4 +40,21 @@ public static class DataManipulationHelpers
         }
         return newList;
     }
+
+    public static List<List<TType>> IterateData<TType>(this List<List<TType>> data, Action<TType, int, int> iterator)
+    {
+        int y = data.Count;
+        foreach(var rowList in data)
+        {
+            y--;
+            int x = 0;
+            foreach(var item in rowList)
+            {
+                iterator(item, x, y);
+                x++;
+            }
+        }
+        
+        return data;
+    }
 }

TextParser/Data/DataSetManipulatorBase.cs

@@ -98,6 +98,8 @@ public abstract class DataSetManipulatorBase<TCollectedType, TDataType, TIndexTy
     // we do not know how to iterate a specific data set exactly, but we only need to find specific items to be able to continue with any other algorithm
     public abstract List<SearchResult<TIndexType>> FindInSet(TDataType data);
 
+    public abstract List<SearchResult<TIndexType>> GetAllItems();
+
     public List<DirectionalSearchResult<TIndexType>> FindAtPosition(IDataIndex<TIndexType> currentPosition, List<TDataType> data)
     {
         return this.FindAtPosition(currentPosition, data, this.ValidDirections());

TextParser/Data/DefaultTwoDimensionalManipulator.cs

@@ -61,6 +61,22 @@ public class DefaultTwoDimensionalManipulator<TDataType> : DataSetManipulatorBas
         }
     }
 
+    public override List<SearchResult<TIndexType>> GetAllItems()
+    {
+        var results = new List<SearchResult<int>>();
+
+        for (int y = 0; y < this.dataSet.Count; y++)
+        {
+            for (int x = 0; x < this.dataSet[this.dataSet.Count - y - 1].Count; x++)
+            {
+                var singleResult = new SearchResult<int>(new DefaultPositionalDataIndex(x, y));
+                results.Add(singleResult);
+            }
+        }
+
+        return results;
+    }
+
     public override List<SearchResult<int>> FindInSet(TDataType data)
     {
         var results = new List<SearchResult<int>>();

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: " + token.GetText());
+                    Type t = token.GetType();
+                    throw new Exception("Provided token is not a ValueToken - type: " + t.ToString() + " assigned to " + typeof(IValueToken<U>).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/Data/TwoDimensionalDataWalker.cs

@@ -0,0 +1,91 @@
+var manipulator = DefaultTwoDimensionalManipulator.Create(row);
+
+using System.Runtime.InteropServices;
+using Parsing.Data;
+
+namespace Parsing.Data;
+
+public static class TwoDimensionalDataWalker
+{
+    public static TwoDimensionalDataWalker<TDataType> Create<TDataType>(List<List<TDataType>> dataSet) where TDataType : IEquatable<TDataType>
+    {
+        return new TwoDimensionalDataWalker<TDataType>(dataSet);
+    }
+}
+
+public class TwoDimensionalDataWalker<TDataType> where TDataType : IEquatable<TDataType>
+{
+    private List<List<TDataType>> dataSet
+
+    private Func<TDataType, bool> startCondition;
+    private TDataType startValue;
+    private bool startValueSet = false;
+    private Func<List<TDataType>, TDataType, bool> walkCondition;
+    private Func<List<TDataType>, TDataType, bool> endCondition;
+    private Direction directions;
+    private DefaultTwoDimenstionalManipulator<TDataType> manipulator;
+
+    public TwoDimensionalDataWalker(List<List<TDataType>> dataSet)
+    {
+        this.dataSet = dataSet;
+        this.manipulator = DefaultTwoDimenstionalManipulator.Create(dataSet);
+    }
+
+    public TwoDimensionalDataWalker<TDataType> WithStartCondition(Func<TDataType, bool> startCondition)
+    {
+        this.startCondition = startCondition;
+        return this;
+    }
+
+    public TwoDimensionalDataWalker<TDataType> WithStartValue(TDataType startValue)
+    {
+        this.startValue = startValue;
+        this.startValueSet = true;
+        return this;
+    }
+
+    public TwoDimensionalDataWalker<TDataType> WithStepCondition(Func<List<TDataType>, TDataType, bool> stepCondition)
+    {
+        this.stepCondition = stepCondition;
+        return this;
+    }
+
+    public TwoDimensionalDataWalker<TDataType> WithEndCondition(Func<List<TDataType>, TDataType, bool> endCondition)
+    {
+        this.endCondition = endCondition;
+        return this;
+    }
+
+    public TwoDimensionalDataWalker<TDataType> WithDirections(Direction directions)
+    {
+        this.directions = directions;
+        return this;
+    }
+
+    private List<List<DirectionalSearchResult<int>>> WalkFromSingleStartPosition(SearchResult<int> start)
+    {
+
+    }
+
+    public List<List<DirectionalSearchResult<int>>> Walk()
+    {
+        List<SearchResult<int>> startingPoints;
+
+        if(this.startValueSet)
+        {
+            startingPoints = manipulator.FindInSet(this.startValue);
+        }
+        else
+        {
+            startingPoints = manipulator.GetAllItems();
+        }
+
+        var allFoundPaths = new List<List<DirectionalSearchResult<int>>>();
+
+        foreach(var startingPoint in startingPoints)
+        {
+            allFoundPaths.AddRange(this.WalkFromSingleStartPosition(startingPoint));
+        }
+        return allFoundPaths;
+    }
+}

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

@@ -28,11 +28,17 @@ 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
-        IntegerBlock intBlock = new IntegerBlock();
-        if (intBlock.CanParseWord(word))
-        {
-            return false;
-        }
+        // LongBlock longBlock = new LongBlock();
+        // if (longBlock.CanParseWord(word))
+        // {
+        //     return false;
+        // }
+
+        // IntegerBlock intBlock = new IntegerBlock();
+        // if (intBlock.CanParseWord(word))
+        // {
+        //     return false;
+        // }
 
         return true;
     }

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