release: version 0.12.0 🚀

This reverts commit 414c74be84.

.gitea/workflows/release.yml

@@ -57,12 +57,6 @@ jobs:
       run: |      
         REPOSITORY_OWNER=$(echo "$GITHUB_REPOSITORY" | awk -F '/' '{print $1}')
         REPOSITORY_NAME=$(echo "$GITHUB_REPOSITORY" | awk -F '/' '{print $2}' | tr '-' '_')
-        REPOSITORY_SOURCE_NAME=gitea-repo
-        if [ -z "$(dotnet nuget config get all | grep "/packages/${REPOSITORY_OWNER}/nuget/index.json")" ]; then
-          dotnet nuget add source --name $REPOSITORY_SOURCE_NAME https://git.disi.dev/api/packages/$REPOSITORY_OWNER/nuget/index.json
-        else
-          QUOTED_REPOSITORY_SOURCE_NAME=$(dotnet nuget config get all | grep "/packages/${REPOSITORY_OWNER}/nuget/index.json" | awk '{print $2}' | awk -F= '{print $2}')
-          REPOSITORY_SOURCE_NAME=${QUOTED_REPOSITORY_SOURCE_NAME:1:-1}
-        fi
         dotnet pack --include-symbols --include-source -p:PackageVersion=$(cat $REPOSITORY_NAME/VERSION) TextParser.sln
-        dotnet nuget push -k $GITEA_PAT --source $REPOSITORY_SOURCE_NAME $REPOSITORY_NAME/bin/Release/$REPOSITORY_NAME.$(cat $REPOSITORY_NAME/VERSION).symbols.nupkg
+        echo "dotnet nuget push -k ${GITEA_PAT:0:-15} $REPOSITORY_NAME/bin/Release/$REPOSITORY_NAME.$(cat $REPOSITORY_NAME/VERSION).symbols.nupkg"
+        dotnet nuget push -k $GITEA_PAT $REPOSITORY_NAME/bin/Release/$REPOSITORY_NAME.$(cat $REPOSITORY_NAME/VERSION).symbols.nupkg

HISTORY.md

@@ -1,172 +0,0 @@
-Changelog
-=========
-
-
-(unreleased)
-------------
-
-Fix
-~~~
-- Remove duplicate TokenConverter definition, ref: NOISSUE. [Simon
-  Diesenreiter]
-
-
-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]
-
-
-0.8.0 (2024-12-12)
-------------------
-- Feat: adding sensible index constructors refs: NOISSUE. [Simon
-  Diesenreiter]
-
-
-0.7.2 (2024-12-05)
-------------------
-
-Fix
-~~~
-- Add some missing API methods, ref: NOISSUE. [Simon Diesenreiter]
-
-Other
-~~~~~
-
-
-0.7.1 (2024-12-05)
-------------------
-
-Fix
-~~~
-- Allow for parsing single chars as input, ref: NOISSUE. [Simon
-  Diesenreiter]
-
-Other
-~~~~~
-
-
-0.7.0 (2024-12-05)
-------------------
-- Feat: implement generic data set manipulator, ref: NOISSUE. [Simon
-  Diesenreiter]
-
-
-0.6.0 (2024-12-03)
-------------------
-- Feat: enable named literals, ref: NOISSUE. [Simon Diesenreiter]
-
-
-0.5.1 (2024-12-03)
-------------------
-
-Fix
-~~~
-- Some bugfixes with fragment parser logic, ref: NOISSUE. [Simon
-  Diesenreiter]
-
-Other
-~~~~~
-
-
-0.5.0 (2024-12-03)
-------------------
-
-Fix
-~~~
-- Fix bugs with fragment parsing support, refs: NOISSUE. [Simon
-  Diesenreiter]
-
-Other
-~~~~~
-- Feat: initial support for fragment parsing, ref: NOISSUE. [Simon
-  Diesenreiter]
-
-
-0.4.0 (2024-12-02)
-------------------
-- Style: fix linting errors, ref: NOISSUE. [Simon Diesenreiter]
-- Feat: implement greedy repetition, ref: A24-13. [Simon Diesenreiter]
-
-
-0.3.0 (2024-12-02)
-------------------
-- Feat: ci pipeline fix for releases, ref NOISSUE. [Simon Diesenreiter]
-
-
-0.2.3 (2024-12-02)
-------------------
-
-Fix
-~~~
-- More release script fixes,ref: NOISSUE. [Simon Diesenreiter]
-
-Other
-~~~~~
-
-
-0.2.2 (2024-12-02)
-------------------
-
-Fix
-~~~
-- Increment version,refs:NOISSUE. [Simon Diesenreiter]
-
-Other
-~~~~~
-
-
-0.2.1 (2024-12-02)
-------------------
-
-Fix
-~~~
-- Fix file inclusion in tag commits, ref: NOISSUE. [Simon Diesenreiter]
-
-
-0.2.0 (2024-12-02)
-------------------
-
-Fix
-~~~
-- Fix some bugs and tests, ref: A24-3. [Simon Diesenreiter]
-
-Other
-~~~~~
-- Ci: fix release shortcut, ref: NOISSUE. [Simon Diesenreiter]
-- Feat: add text parser and output format options, ref: A24-3. [Simon
-  Diesenreiter]
-
-
-0.1.0 (2024-12-01)
-------------------
-- Feat: added initial implementation of TextParser, ref: A24-3. [Simon
-  Diesenreiter]
-- ✅ Ready to clone and code. [simon]
-- Ci: initial commit for triggering migration, ref: NOISSUE. [Simon
-  Diesenreiter]
-- Initial commit. [Projects <>]
-
-

TextParser.Tests/TextParserTests.cs

@@ -34,6 +34,7 @@ public class TextParserTests
                                          bca 
                                          cab";
     private const string testInput11 = @"2 x y 4 x y 6 x y 4 x y 1 x y";
+    private const string testInput12 = @"abcd";
 
     [Fact]
     public void LineParser_TestSimpleRepetition()
@@ -443,4 +444,27 @@ public class TextParserTests
         Assert.Equal(4, numbers[3]);
         Assert.Equal(1, numbers[4]);
     }
+
+    [Fact]
+    public void TextParser_TestCharExplicit()
+    {
+        var schemaBuilder = new InputSchemaBuilder();
+        var schema = schemaBuilder
+                        .Repeat()
+                            .Expect(InputType.Char)
+                        .EndRepetition()
+                        .Build();
+
+        var parser = new TextParser<InputSchemaContext>(schema);
+        var numbers = parser
+                        .SetInputText(testInput12)
+                        .Parse()
+                        .AsSingleStream<string>();
+
+        Assert.Equal(4, numbers.Count);
+        Assert.Equal("a", numbers[0]);
+        Assert.Equal("b", numbers[1]);
+        Assert.Equal("c", numbers[2]);
+        Assert.Equal("d", numbers[3]);
+    }
 }

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/CharBlock.cs

@@ -44,6 +44,6 @@ class CharBlock : BuildingBlockBase
 
     public override BlockType GetBlockType()
     {
-        return BlockType.String;
+        return BlockType.Char;
     }
 }

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/FragmentSchema.cs

@@ -17,6 +17,7 @@ public class FragmentSchema : ISchema<FragmentSchemaContext>
     private string fragmentRegex;
     private List<string> namedGroups = new List<string>();
     private List<string> namedLiterals = new List<string>();
+    private bool ignoreEmptyMatches = true;
 
     public FragmentSchema(string fragmentRegex, List<string> namedGroups, List<string> namedLiterals)
     {
@@ -33,6 +34,11 @@ public class FragmentSchema : ISchema<FragmentSchemaContext>
         // one token per match
         foreach (Match match in r.Matches(inputs.YieldWord()))
         {
+            if(this.ignoreEmptyMatches && string.IsNullOrEmpty(match.Value))
+            {
+                continue;
+            }
+
             var newToken = new FragmentToken(match.Value);
             // token contains data from all included matches
             foreach (var groupName in this.namedGroups)
@@ -109,4 +115,9 @@ public class FragmentSchema : ISchema<FragmentSchemaContext>
     {
         return new FragmentSchemaContext();
     }
+
+    public void ShouldIgnoreEmptyMatches(bool ignoreEmptyMatches)
+    {
+        this.ignoreEmptyMatches = ignoreEmptyMatches;
+    }
 }

TextParser/Schema/FragmentSchemaBuilder.cs

@@ -52,12 +52,22 @@ public class FragmentSchemaBuilder : RepetitionSchemaBuilder<FragmentSchemaBuild
             case InputType.Integer:
                 this.fragmentRegex += "(" + groupNamePrefix + "\\d+)";
                 break;
+            case InputType.Char:
+                this.fragmentRegex += "(" + groupNamePrefix + "[a-zA-Z])";
+                break;
             default:
                 throw new Exception("Unrecognized InputType");
         }
         return this;
     }
 
+    public FragmentSchemaBuilder ShouldIgnoreEmptyMatches(bool ignoreEmptyMatches)
+    {
+        this.ShouldIgnoreEmptyMatches(ignoreEmptyMatches);
+
+        return this;
+    }
+
     public FragmentSchemaBuilder Expect(string literal, string name = "")
     {
         string groupNamePrefix = "";
@@ -130,6 +140,10 @@ public class FragmentSchemaBuilder : RepetitionSchemaBuilder<FragmentSchemaBuild
         }
 
         oldSchemaBuilder.fragmentRegex += "(" + currentRegex + ")";
+        var groupsToAdd = currentBuilder.namedGroups.Where(g => !oldSchemaBuilder.namedGroups.Contains(g)).ToList();
+        var literalsToAdd = currentBuilder.namedLiterals.Where(l => !oldSchemaBuilder.namedLiterals.Contains(l)).ToList();
+        oldSchemaBuilder.namedGroups.AddRange(groupsToAdd);
+        oldSchemaBuilder.namedLiterals.AddRange(literalsToAdd);
 
         return oldSchemaBuilder;
     }

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
+0.12.0

nuget.config

@@ -8,4 +8,8 @@
     <add key="gitea-homelab" value="https://git.disi.dev/api/packages/Homelab/nuget/index.json" />
     <add key="gitea-artifacts" value="https://git.disi.dev/api/packages/Artifacts/nuget/index.json" />
   </packageSources>
+
+  <config>
+    <add key="DefaultPushSource" value="https://git.disi.dev/api/packages/Projects/nuget/index.json" />
+  </config>
 </configuration>