release: version 0.10.0 🚀

HISTORY.md

@@ -4,6 +4,46 @@ 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)
+------------------
+
+Fix
+~~~
+- More bugfixes, ref: NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.1 (2024-12-13)
+------------------
+
+Fix
+~~~
+- Fix build issues, ref: NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.0 (2024-12-13)
+------------------
 - Feat: add filter option to TokenConverter, ref: NOISSUE. [Simon
   Diesenreiter]
 

TextParser.Tests/TextParserTests.cs

@@ -33,6 +33,7 @@ public class TextParserTests
     private const string testInput10 = @"abc 
                                          bca 
                                          cab";
+    private const string testInput11 = @"2 x y 4 x y 6 x y 4 x y 1 x y";
 
     [Fact]
     public void LineParser_TestSimpleRepetition()
@@ -394,7 +395,7 @@ public class TextParserTests
     }
 
     [Fact]
-    public void TextPArser_TestReadingChars()
+    public void TextParser_TestReadingChars()
     {
         var schemaBuilder = new InputSchemaBuilder();
         var schema = schemaBuilder
@@ -415,4 +416,31 @@ public class TextParserTests
         Assert.Equal(3, row[1].Count);
         Assert.Equal(3, row[2].Count);
     }
+
+    [Fact]
+    public void TextParser_TestFilter()
+    {
+        var schemaBuilder = new InputSchemaBuilder();
+        var schema = schemaBuilder
+                        .Repeat()
+                            .Expect(InputType.Integer)
+                            .Expect(InputType.Char)
+                            .Expect(InputType.Char)
+                        .EndRepetition()
+                        .Build();
+
+        var parser = new TextParser<InputSchemaContext>(schema);
+        var numbers = parser
+                        .SetInputText(testInput11)
+                        .Parse()
+                        .Filter(InputType.Integer)
+                        .AsSingleStream<int>();
+
+        Assert.Equal(5, numbers.Count);
+        Assert.Equal(2, numbers[0]);
+        Assert.Equal(4, numbers[1]);
+        Assert.Equal(6, numbers[2]);
+        Assert.Equal(4, numbers[3]);
+        Assert.Equal(1, numbers[4]);
+    }
 }

TextParser/Data/DataManipulationHelpers.cs

@@ -36,7 +36,7 @@ public static class DataManipulationHelpers
         var newList = new List<TNewType>();
         foreach (List<TType> dataItemList in data)
         {
-            newList.Add(transformer(dataItem));
+            newList.Add(transformer(dataItemList));
         }
         return newList;
     }

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());
             }
 
@@ -157,19 +161,24 @@ public class TokenConverter
         return newList;
     }
 
-    public TokenConverter Filter<T>(params InputType[] inputTypes)
+    public TokenConverter Filter(params InputType[] inputTypes)
     {
-        var newTokenList = new List<List<IToken>>()
+        var newTokenListList = new List<List<IToken>>();
         
-        foreach(var token in rawTokens)
+        foreach(var tokenList in this.rawTokens)
         {
-            if(inputTypes.Contains(token.GetInputType()))
+            var newTokenList = new List<IToken>();
+            foreach(var token in tokenList)
             {
-                newTokenList.Add(token);
+                if(inputTypes.Contains(token.GetInputType()))
+                {
+                    newTokenList.Add(token);
+                }
             }
+            newTokenListList.Add(newTokenList);
         }
 
-        this.rawTokens = newTokenList;
+        this.rawTokens = newTokenListList;
 
         return this;
     }

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/TokenConverter.cs

@@ -1,226 +0,0 @@
-namespace Parsing;
-
-using System;
-using System.Collections.Generic;
-using Parsing.Schema;
-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>
-    {
-        var newList = new List<TNewType>();
-        foreach (var token in tokenList)
-        {
-            var typedToken = token as IValueToken<TOldType>;
-            if (typedToken == null)
-            {
-                throw new Exception("Invalid Token type encountered during value conversion");
-            }
-
-            newList.Add(converter(typedToken.GetValue()));
-        }
-        return newList;
-    }
-
-    public static List<TNewType> ConvertData<TTokenType, TNewType, TOldType>(this List<IToken> tokenList, Func<TOldType, List<TNewType>> converter) where TTokenType : IValueToken<TOldType>
-    {
-        var newList = new List<TNewType>();
-        foreach (var token in tokenList)
-        {
-            var typedToken = token as IValueToken<TOldType>;
-            if (typedToken == null)
-            {
-                throw new Exception("Invalid Token type encountered during value conversion");
-            }
-
-            newList.AddRange(converter(typedToken.GetValue()));
-        }
-        return newList;
-    }
-
-    public static List<List<TNewType>> ConvertData<TTokenType, TNewType, TOldType>(this List<List<IToken>> tokenListList, Func<TOldType, TNewType> converter) where TTokenType : IValueToken<TOldType>
-    {
-        var newListList = new List<List<TNewType>>();
-        foreach (var tokenList in tokenListList)
-        {
-            newListList.Add(tokenList.ConvertData<TTokenType, TNewType, TOldType>(converter));
-        }
-        return newListList;
-    }
-}
-
-public static class DataManipulationHelpers
-{
-    public static TType ReduceData<TType>(this List<TType> data, Func<TType, TType, TType> reducer)
-    {
-        if (data.Count < 2)
-        {
-            return data[0];
-        }
-        TType result = data[0];
-        for (int i = 1; i < data.Count; i++)
-        {
-            result = reducer(result, data[i]);
-        }
-        return result;
-    }
-
-    public static TType ReduceData<TType>(this List<TType> data, Func<List<TType>, TType> reducer)
-    {
-        return reducer(data);
-    }
-}
-
-public class TokenConverter
-{
-    protected List<List<IToken>> rawTokens = new List<List<IToken>>();
-
-    public TokenConverter()
-    {
-    }
-
-    private List<T> AsGenericCollection<T, U>() where T : ICollection<U>, new()
-    {
-        List<T> returnData = new List<T>();
-        foreach (var tokenRow in this.rawTokens)
-        {
-            T newRow = new T();
-            foreach (IToken token in tokenRow)
-            {
-                if (token == null)
-                {
-                    throw new Exception("No token was provided, but token was expected!");
-                }
-                IValueToken<U>? valueToken = token as IValueToken<U>;
-                if (valueToken == null)
-                {
-                    throw new Exception("Provided token is not a ValueToken");
-                }
-                newRow.Add(valueToken.GetValue());
-            }
-
-            returnData.Add(newRow);
-        }
-        return returnData;
-    }
-
-    private void CheckConversionPrerequisites()
-    {
-        // in order to convert rows to columns or grid we require every row to have the same length
-        int rowLength = this.rawTokens[0].Count;
-
-        foreach (var tokenRow in this.rawTokens)
-        {
-            if (tokenRow.Count != rowLength)
-            {
-                throw new Exception("Attempted to convert token dataset that is not able to be converted!");
-            }
-        }
-    }
-
-    public List<T> AsSingleStream<T>()
-    {
-        List<T> returnData = new List<T>();
-        foreach (var tokenRow in this.rawTokens)
-        {
-            foreach (IToken token in tokenRow)
-            {
-                if (token == null)
-                {
-                    throw new Exception("No token was provided, but token was expected!");
-                }
-                IValueToken<T>? valueToken = token as IValueToken<T>;
-                if (valueToken == null)
-                {
-                    throw new Exception("Provided token is not a ValueToken");
-                }
-                returnData.Add(valueToken.GetValue());
-            }
-        }
-        return returnData;
-    }
-
-    public List<T[]> AsRows<T>()
-    {
-        var listRows = this.AsListRows<T>();
-        var newList = new List<T[]>();
-
-        foreach (var rowList in listRows)
-        {
-            newList.Add(rowList.ToArray());
-        }
-
-        return newList;
-    }
-
-    public List<List<T>> AsListRows<T>()
-    {
-        return this.AsGenericCollection<List<T>, T>();
-    }
-
-    public List<T[]> AsColumns<T>()
-    {
-        var listColumns = this.AsListColumns<T>();
-        var newList = new List<T[]>();
-
-        foreach (var columnList in listColumns)
-        {
-            newList.Add(columnList.ToArray());
-        }
-
-        return newList;
-    }
-
-    public List<List<T>> AsListColumns<T>()
-    {
-        this.CheckConversionPrerequisites();
-        var rows = AsListRows<T>();
-
-        var columns = new List<List<T>>();
-        for (int i = 0; i < rows[0].Count; i++)
-        {
-            columns.Add(new List<T>());
-        }
-
-        foreach (var row in rows)
-        {
-            for (int i = 0; i < row.Count; i++)
-            {
-                columns[i].Add(row[i]);
-            }
-        }
-
-        return columns;
-    }
-
-    public T[][] AsGrid<T>()
-    {
-        this.CheckConversionPrerequisites();
-        var rowsList = AsRows<T>();
-        return rowsList.ToArray();
-    }
-
-    public List<List<IToken>> AsRawData()
-    {
-        return this.rawTokens;
-    }
-
-    public List<Fragment> AsFragments()
-    {
-        var items = this.AsSingleStream<Fragment>();
-        var newList = new List<Fragment>();
-
-        foreach (var item in items)
-        {
-            var typedItem = item as Fragment;
-            if (typedItem == null)
-            {
-                throw new Exception("Invalid token type encountered");
-            }
-            newList.Add(typedItem);
-        }
-
-        return newList;
-    }
-}

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 @@
-0.9.0
+0.10.0