14 Commits
0.7.0 ... 0.9.3

Author SHA1 Message Date
0f533c2018 release: version 0.9.3 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 19s
Upload Python Package / deploy (push) Failing after 4m3s
2024-12-13 13:50:04 +01:00
2067fe06fc fix: remove duplicate TokenConverter definition, ref: NOISSUE 2024-12-13 13:50:01 +01:00
cc0f0a24d9 release: version 0.9.2 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 18s
Upload Python Package / deploy (push) Failing after 4m6s
2024-12-13 13:30:50 +01:00
c41d665ab8 fix: more bugfixes, ref: NOISSUE 2024-12-13 13:30:46 +01:00
2fbdafa0e9 release: version 0.9.1 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 19s
Upload Python Package / deploy (push) Failing after 4m4s
2024-12-13 13:23:06 +01:00
f942954678 fix: fix build issues, ref: NOISSUE 2024-12-13 13:23:02 +01:00
4c67e8efb0 release: version 0.9.0 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 17s
Upload Python Package / deploy (push) Failing after 4m23s
2024-12-13 13:13:50 +01:00
e83e99758a feat: add filter option to TokenConverter, ref: NOISSUE 2024-12-13 13:13:43 +01:00
81ac797b4c release: version 0.8.0 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 17s
Upload Python Package / deploy (push) Failing after 4m6s
2024-12-12 20:03:14 +01:00
e9aa60524c feat: adding sensible index constructors refs: NOISSUE 2024-12-12 20:03:07 +01:00
7e5ab9f799 release: version 0.7.2 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 17s
Upload Python Package / deploy (push) Failing after 4m24s
2024-12-06 00:33:43 +01:00
fc137ebd03 fix: add some missing API methods, ref: NOISSUE 2024-12-06 00:33:37 +01:00
1b2e9ad1ee release: version 0.7.1 🚀
Some checks failed
Upload Python Package / Create Release (push) Successful in 17s
Upload Python Package / deploy (push) Failing after 4m25s
2024-12-06 00:03:23 +01:00
550c8280a6 fix: allow for parsing single chars as input, ref: NOISSUE 2024-12-05 23:58:11 +01:00
19 changed files with 257 additions and 32 deletions

View File

@@ -4,6 +4,72 @@ 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]

View File

@@ -30,6 +30,10 @@ public class TextParserTests
private const string testInput9 = @"2 4 6 4 1
3 5 4 7 6
4 6 8 3 9";
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()
@@ -322,7 +326,7 @@ public class TextParserTests
[Fact]
public void DataManipulator_SimpleOneDimensionalTest()
{
{
var schemaBuilder = new InputSchemaBuilder();
var schema = schemaBuilder
.Repeat()
@@ -351,7 +355,7 @@ public class TextParserTests
[Fact]
public void DataManipulator_SimpleTwoDimensionalTest()
{
{
var schemaBuilder = new InputSchemaBuilder();
var schema = schemaBuilder
.Repeat()
@@ -389,4 +393,54 @@ public class TextParserTests
Assert.Equal(Direction.SE, searchResults[4].Direction);
Assert.Equal(Direction.W, searchResults[5].Direction);
}
[Fact]
public void TextParser_TestReadingChars()
{
var schemaBuilder = new InputSchemaBuilder();
var schema = schemaBuilder
.Repeat()
.Expect(InputType.Char)
.EndRepetition()
.Build();
var parser = new TextParser<InputSchemaContext>(schema);
var row = parser
.SetInputText(testInput10)
.Parse()
.AsListRows<string>();
Assert.Equal(3, row.Count);
Assert.Equal("a", row[0][0]);
Assert.Equal(3, row[0].Count);
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]);
}
}

View File

@@ -20,4 +20,24 @@ public static class DataManipulationHelpers
{
return reducer(data);
}
public static List<TNewType> TransformData<TType, TNewType>(this List<TType> data, Func<TType, TNewType> transformer)
{
var newList = new List<TNewType>();
foreach (TType dataItem in data)
{
newList.Add(transformer(dataItem));
}
return newList;
}
public static List<TNewType> TransformData<TType, TNewType>(this List<List<TType>> data, Func<List<TType>, TNewType> transformer)
{
var newList = new List<TNewType>();
foreach (List<TType> dataItemList in data)
{
newList.Add(transformer(dataItemList));
}
return newList;
}
}

View File

@@ -4,11 +4,22 @@ namespace Parsing.Data;
public class SearchResult<TIndexType>
{
public SearchResult(IDataIndex<TIndexType> dataIndex)
{
this.DataIndex = dataIndex;
}
public IDataIndex<TIndexType>? DataIndex { get; set; }
}
public class DirectionalSearchResult<TIndexType> : SearchResult<TIndexType>
{
public DirectionalSearchResult(IDataIndex<TIndexType> dataIndex, Direction direction, int length): base(dataIndex)
{
this.Direction = direction;
this.Length = length;
}
public Direction Direction { get; set; }
public int Length { get; set; }
}
@@ -111,10 +122,7 @@ public abstract class DataSetManipulatorBase<TCollectedType, TDataType, TIndexTy
}
if (searchIndex == data.Count)
{
var result = new DirectionalSearchResult<TIndexType>();
result.DataIndex = currentPosition;
result.Direction = direction;
result.Length = searchIndex;
var result = new DirectionalSearchResult<TIndexType>(currentPosition, direction, searchIndex);
results.Add(result);
}
}
@@ -123,7 +131,7 @@ public abstract class DataSetManipulatorBase<TCollectedType, TDataType, TIndexTy
return results;
}
public List<DirectionalSearchResult<TIndexType>> FindInSet(List<TDataType> data)
public List<DirectionalSearchResult<TIndexType>> FindInSet(List<TDataType> data, Direction directions)
{
var result = new List<DirectionalSearchResult<TIndexType>>();
@@ -131,11 +139,16 @@ public abstract class DataSetManipulatorBase<TCollectedType, TDataType, TIndexTy
var startingPoints = this.FindInSet(data[0]);
foreach (var startingPoint in startingPoints)
{
foreach (var results in this.FindAtPosition(startingPoint.DataIndex, data))
foreach (var results in this.FindAtPosition(startingPoint.DataIndex, data, directions))
{
result.AddRange(results);
}
}
return result;
}
public List<DirectionalSearchResult<TIndexType>> FindInSet(List<TDataType> data)
{
return this.FindInSet(data, this.ValidDirections());
}
}

View File

@@ -49,8 +49,7 @@ public class DefaultOneDimensionalManipulator<TDataType> : DataSetManipulatorBas
{
if (EqualityComparer<TDataType>.Default.Equals(this.dataSet[i], data))
{
var singleResult = new SearchResult<int>();
singleResult.DataIndex = new DefaultPositionalDataIndex(i);
var singleResult = new SearchResult<int>(new DefaultPositionalDataIndex(i));
results.Add(singleResult);
}
}

View File

@@ -71,8 +71,7 @@ public class DefaultTwoDimensionalManipulator<TDataType> : DataSetManipulatorBas
{
if (EqualityComparer<TDataType>.Default.Equals(this.dataSet[this.dataSet.Count - y - 1][x], data))
{
var singleResult = new SearchResult<int>();
singleResult.DataIndex = new DefaultPositionalDataIndex(x, y);
var singleResult = new SearchResult<int>(new DefaultPositionalDataIndex(x, y));
results.Add(singleResult);
}
}

View File

@@ -156,4 +156,26 @@ public class TokenConverter
return newList;
}
public TokenConverter Filter(params InputType[] inputTypes)
{
var newTokenListList = new List<List<IToken>>();
foreach(var tokenList in rawTokens)
{
var newTokenList = new List<IToken>();
foreach(var token in tokenList)
{
if(inputTypes.Contains(token.GetInputType()))
{
newTokenList.Add(token);
}
}
newTokenListList.Add(newTokenList);
}
this.rawTokens = newTokenListList;
return this;
}
}

View File

@@ -4,10 +4,11 @@
public enum BlockType
{
Integer = 1,
String = 2,
Char = 2,
String = 4,
// technically not a block type but keeping it here for consistency/having all types in one place
Fragment = 4,
FixedRepetition = 8,
GreedyRepetition = 16,
NonZeroRepetition = 32,
Fragment = 8,
FixedRepetition = 16,
GreedyRepetition = 32,
NonZeroRepetition = 64,
}

View File

@@ -8,7 +8,7 @@ abstract class BuildingBlockBase : IBuildingBlock
{
}
public abstract IToken ParseWord(InputProvider inputs);
public abstract List<IToken> ParseWord(InputProvider inputs);
public abstract bool CanParseWord(InputProvider inputs);

View File

@@ -0,0 +1,49 @@
namespace Parsing.Schema.BuildingBlocks;
using Parsing.Tokenization;
class CharBlock : BuildingBlockBase
{
public CharBlock()
{
}
public override List<IToken> ParseWord(InputProvider inputs)
{
var tokenList = new List<IToken>();
foreach (char c in inputs.YieldWord())
{
tokenList.Add(new StringToken(c.ToString()));
}
return tokenList;
}
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)
{
// 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;
}
return true;
}
public override BlockType GetBlockType()
{
return BlockType.String;
}
}

View File

@@ -20,7 +20,7 @@ class FixedRepetitionBlock : BuildingBlockBase
this.context = this.inputSchema.CreateContext();
}
public override IToken ParseWord(InputProvider inputs)
public override List<IToken> ParseWord(InputProvider inputs)
{
var result = inputSchema.ProcessNextWord(context, inputs);
if (context.HasFinished)
@@ -31,7 +31,7 @@ class FixedRepetitionBlock : BuildingBlockBase
this.context = this.inputSchema.CreateContext();
}
}
return result.Single();
return result;
}
public override bool CanParseWord(InputProvider inputs)

View File

@@ -15,14 +15,14 @@ class GreedyRepetitionBlock : BuildingBlockBase
this.context = this.inputSchema.CreateContext();
}
public override IToken ParseWord(InputProvider inputs)
public override List<IToken> ParseWord(InputProvider inputs)
{
var result = inputSchema.ProcessNextWord(context, inputs);
if (!this.CanParseWord(inputs))
{
this.context = this.inputSchema.CreateContext();
}
return result.Single();
return result;
}
public override bool CanParseWord(InputProvider inputs)

View File

@@ -4,7 +4,7 @@ using Parsing.Tokenization;
public interface IBuildingBlock
{
public IToken ParseWord(InputProvider inputs);
public List<IToken> ParseWord(InputProvider inputs);
public bool CanParseWord(InputProvider inputs);

View File

@@ -9,9 +9,9 @@ class IntegerBlock : BuildingBlockBase
{
}
public override IToken ParseWord(InputProvider inputs)
public override List<IToken> ParseWord(InputProvider inputs)
{
return new IntegerToken(inputs.YieldWord());
return new List<IToken>() { new IntegerToken(inputs.YieldWord()) };
}
public override bool CanParseWord(InputProvider inputs)

View File

@@ -9,9 +9,9 @@ class StringBlock : BuildingBlockBase
{
}
public override IToken ParseWord(InputProvider inputs)
public override List<IToken> ParseWord(InputProvider inputs)
{
return new StringToken(inputs.YieldWord());
return new List<IToken>() { new StringToken(inputs.YieldWord()) };
}
public override bool CanParseWord(InputProvider inputs)

View File

@@ -28,15 +28,13 @@ public class InputSchema : ISchema<InputSchemaContext>
public List<IToken> ProcessNextWord(InputSchemaContext currentContext, InputProvider inputs)
{
var nextBlock = this.buildingBlocks[currentContext.lastProcessedBlockIndex];
var token = nextBlock.ParseWord(inputs);
var tokens = nextBlock.ParseWord(inputs);
if (!nextBlock.IsRepetitionType() || nextBlock.CheckIsDoneParsingAndReset(inputs))
{
currentContext.lastProcessedBlockIndex++;
currentContext.HasFinished = currentContext.lastProcessedBlockIndex >= this.buildingBlocks.Count;
}
var newTokenList = new List<IToken>();
newTokenList.Add(token);
return newTokenList;
return tokens;
}
public bool CanProcessNextWord(InputSchemaContext currentContext, InputProvider inputs)

View File

@@ -21,6 +21,9 @@ public class InputSchemaBuilder : RepetitionSchemaBuilder<InputSchemaBuilder, In
case InputType.Integer:
block = new IntegerBlock();
break;
case InputType.Char:
block = new CharBlock();
break;
default:
throw new Exception("Unrecognized InputType");
}

View File

@@ -6,4 +6,5 @@ public enum InputType
Integer = BlockType.Integer,
String = BlockType.String,
Fragment = BlockType.Fragment,
Char = BlockType.Char,
}

View File

@@ -1 +1 @@
0.7.0
0.9.3