parent
dbbab1c761
commit
0fdfef8854
|
@ -13,5 +13,7 @@ jobs:
|
|||
path: ~/.nuget/packages
|
||||
key: ${{ runner.os }}-nuget
|
||||
save-always: true
|
||||
- name: Build code
|
||||
run: dotnet build
|
||||
- name: Run test code
|
||||
run: dotnet test
|
||||
|
|
|
@ -4,60 +4,57 @@ namespace Canon.Core.LexicalParser;
|
|||
|
||||
public static class LexemeFactory
|
||||
{
|
||||
|
||||
public static SemanticToken MakeToken(SemanticTokenType tokenType,string literal,uint _line,uint _chPos)
|
||||
public static SemanticToken MakeToken(SemanticTokenType tokenType,string literal,uint line,uint chPos)
|
||||
{
|
||||
SemanticToken? token;
|
||||
switch (tokenType)
|
||||
{
|
||||
case SemanticTokenType.Character:
|
||||
CharacterSemanticToken characterSemanticToken = new CharacterSemanticToken()
|
||||
CharacterSemanticToken characterSemanticToken = new()
|
||||
{
|
||||
LinePos = _line, CharacterPos = _chPos, LiteralValue = literal,
|
||||
LinePos = line, CharacterPos = chPos, LiteralValue = literal,
|
||||
};
|
||||
token = characterSemanticToken;
|
||||
break;
|
||||
case SemanticTokenType.Identifier:
|
||||
IdentifierSemanticToken identifierSemanticToken = new IdentifierSemanticToken()
|
||||
IdentifierSemanticToken identifierSemanticToken = new()
|
||||
{
|
||||
LinePos = _line, CharacterPos = _chPos, LiteralValue = literal,
|
||||
LinePos = line, CharacterPos = chPos, LiteralValue = literal,
|
||||
};
|
||||
token = identifierSemanticToken;
|
||||
break;
|
||||
default:
|
||||
throw new ArgumentOutOfRangeException(nameof(tokenType), tokenType, null);
|
||||
throw new InvalidOperationException("Can only create Character or Identifier SemanticToken.");
|
||||
}
|
||||
|
||||
return token;
|
||||
|
||||
|
||||
}
|
||||
|
||||
public static KeywordSemanticToken MakeToken(KeywordType keywordType,string literal,uint _line,uint _chPos)
|
||||
public static KeywordSemanticToken MakeToken(KeywordType keywordType,string literal,uint line,uint chPos)
|
||||
{
|
||||
KeywordSemanticToken keywordSemanticToken = new KeywordSemanticToken
|
||||
KeywordSemanticToken keywordSemanticToken = new()
|
||||
{
|
||||
LinePos = _line,
|
||||
CharacterPos = _chPos,
|
||||
LinePos = line,
|
||||
CharacterPos = chPos,
|
||||
LiteralValue = literal,
|
||||
KeywordType = keywordType
|
||||
};
|
||||
return keywordSemanticToken;
|
||||
}
|
||||
|
||||
public static DelimiterSemanticToken MakeToken(DelimiterType delimiterType,string literal,uint _line,uint _chPos)
|
||||
public static DelimiterSemanticToken MakeToken(DelimiterType delimiterType,string literal,uint line,uint chPos)
|
||||
{
|
||||
DelimiterSemanticToken delimiterSemanticToken = new DelimiterSemanticToken()
|
||||
DelimiterSemanticToken delimiterSemanticToken = new()
|
||||
{
|
||||
LinePos = _line,
|
||||
CharacterPos = _chPos,
|
||||
LinePos = line,
|
||||
CharacterPos = chPos,
|
||||
LiteralValue = literal,
|
||||
DelimiterType = delimiterType
|
||||
};
|
||||
return delimiterSemanticToken;
|
||||
}
|
||||
|
||||
public static NumberSemanticToken MakeToken(NumberType numberType,string literal,uint _line,uint _chPos)
|
||||
public static NumberSemanticToken MakeToken(NumberType numberType,string literal,uint line,uint chPos)
|
||||
{
|
||||
string temp = literal;
|
||||
string result;
|
||||
|
@ -70,10 +67,10 @@ public static class LexemeFactory
|
|||
result = temp;
|
||||
}
|
||||
|
||||
NumberSemanticToken numberSemanticToken = new NumberSemanticToken()
|
||||
NumberSemanticToken numberSemanticToken = new()
|
||||
{
|
||||
LinePos = _line,
|
||||
CharacterPos = _chPos,
|
||||
LinePos = line,
|
||||
CharacterPos = chPos,
|
||||
LiteralValue = result,
|
||||
NumberType = numberType
|
||||
};
|
||||
|
@ -81,12 +78,12 @@ public static class LexemeFactory
|
|||
|
||||
}
|
||||
|
||||
public static OperatorSemanticToken MakeToken(OperatorType operatorType,string literal,uint _line,uint _chPos)
|
||||
public static OperatorSemanticToken MakeToken(OperatorType operatorType,string literal,uint line,uint chPos)
|
||||
{
|
||||
OperatorSemanticToken operatorSemanticToken = new OperatorSemanticToken()
|
||||
OperatorSemanticToken operatorSemanticToken = new()
|
||||
{
|
||||
LinePos = _line,
|
||||
CharacterPos = _chPos,
|
||||
LinePos = line,
|
||||
CharacterPos = chPos,
|
||||
LiteralValue = literal,
|
||||
OperatorType = operatorType
|
||||
};
|
||||
|
|
|
@ -22,21 +22,10 @@ public class Lexer : ILexer
|
|||
private uint _line = 1;
|
||||
private uint _chPos;
|
||||
|
||||
// Token统计信息
|
||||
private readonly Dictionary<SemanticTokenType, int> _tokenCount = new()
|
||||
{
|
||||
{ SemanticTokenType.Keyword, 0 },
|
||||
{ SemanticTokenType.Number, 0 },
|
||||
{ SemanticTokenType.Operator, 0 },
|
||||
{ SemanticTokenType.Delimiter, 0 },
|
||||
{ SemanticTokenType.Identifier, 0 },
|
||||
{ SemanticTokenType.Character, 0 },
|
||||
{ SemanticTokenType.End, 0 }
|
||||
};
|
||||
|
||||
public IEnumerable<SemanticToken> Tokenize(ISourceReader reader)
|
||||
{
|
||||
_reader = reader;
|
||||
_state = StateType.Start;
|
||||
|
||||
while (_state != StateType.Done)
|
||||
{
|
||||
|
@ -526,7 +515,11 @@ public class Lexer : ILexer
|
|||
break;
|
||||
}
|
||||
|
||||
AddToTokens(_semanticToken);
|
||||
if (_semanticToken is null)
|
||||
{
|
||||
throw new InvalidOperationException();
|
||||
}
|
||||
_tokens.Add(_semanticToken);
|
||||
_state = StateType.Start;
|
||||
}
|
||||
|
||||
|
@ -614,9 +607,6 @@ public class Lexer : ILexer
|
|||
private void AddToTokens(SemanticToken semanticToken)
|
||||
{
|
||||
_tokens.Add(semanticToken);
|
||||
_tokenCount[semanticToken.TokenType]++;
|
||||
Console.WriteLine($"<{semanticToken.TokenType}>");
|
||||
Console.WriteLine(semanticToken.LiteralValue);
|
||||
}
|
||||
|
||||
private void Cat()
|
||||
|
|
|
@ -54,12 +54,13 @@ public abstract class SemanticToken : IEquatable<SemanticToken>
|
|||
/// </summary>
|
||||
public static EndSemanticToken End => new()
|
||||
{
|
||||
LinePos = 0, CharacterPos = 0, LiteralValue = string.Empty
|
||||
LinePos = uint.MaxValue, CharacterPos = uint.MaxValue, LiteralValue = string.Empty
|
||||
};
|
||||
|
||||
public override string ToString()
|
||||
{
|
||||
return $"LinePos: {LinePos}, CharacterPos: {CharacterPos}, LiteralValue: {LiteralValue}, TokenType: {TokenType}";
|
||||
return
|
||||
$"LinePos: {LinePos}, CharacterPos: {CharacterPos}, LiteralValue: {LiteralValue}, TokenType: {TokenType}";
|
||||
}
|
||||
|
||||
public bool Equals(SemanticToken? other)
|
||||
|
@ -93,13 +94,6 @@ public abstract class SemanticToken : IEquatable<SemanticToken>
|
|||
public class CharacterSemanticToken : SemanticToken
|
||||
{
|
||||
public override SemanticTokenType TokenType => SemanticTokenType.Character;
|
||||
|
||||
public static bool TryParse(uint linePos, uint characterPos, LinkedListNode<char> now,
|
||||
out CharacterSemanticToken? token)
|
||||
{
|
||||
token = null;
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
|
@ -146,7 +140,7 @@ public class DelimiterSemanticToken : SemanticToken
|
|||
|
||||
public override int GetHashCode()
|
||||
{
|
||||
return base.GetHashCode() ^ this.DelimiterType.GetHashCode();
|
||||
return base.GetHashCode() ^ DelimiterType.GetHashCode();
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -159,33 +153,34 @@ public class KeywordSemanticToken : SemanticToken
|
|||
|
||||
public required KeywordType KeywordType { get; init; }
|
||||
|
||||
public static readonly Dictionary<string, KeywordType> KeywordTypes = new Dictionary<string, KeywordType>(StringComparer.OrdinalIgnoreCase)
|
||||
{
|
||||
{ "program", KeywordType.Program },
|
||||
{ "const", KeywordType.Const },
|
||||
{ "var", KeywordType.Var },
|
||||
{ "procedure", KeywordType.Procedure },
|
||||
{ "function", KeywordType.Function },
|
||||
{ "begin", KeywordType.Begin },
|
||||
{ "end", KeywordType.End },
|
||||
{ "array", KeywordType.Array },
|
||||
{ "of", KeywordType.Of },
|
||||
{ "if", KeywordType.If },
|
||||
{ "then", KeywordType.Then },
|
||||
{ "else", KeywordType.Else },
|
||||
{ "for", KeywordType.For },
|
||||
{ "to", KeywordType.To },
|
||||
{ "do", KeywordType.Do },
|
||||
{ "integer", KeywordType.Integer },
|
||||
{ "real", KeywordType.Real },
|
||||
{ "boolean", KeywordType.Boolean },
|
||||
{ "character", KeywordType.Character },
|
||||
{ "div", KeywordType.Divide }, // 注意: Pascal 使用 'div' 而不是 '/'
|
||||
{ "not", KeywordType.Not },
|
||||
{ "mod", KeywordType.Mod },
|
||||
{ "and", KeywordType.And },
|
||||
{ "or", KeywordType.Or }
|
||||
};
|
||||
public static readonly Dictionary<string, KeywordType> KeywordTypes =
|
||||
new Dictionary<string, KeywordType>(StringComparer.OrdinalIgnoreCase)
|
||||
{
|
||||
{ "program", KeywordType.Program },
|
||||
{ "const", KeywordType.Const },
|
||||
{ "var", KeywordType.Var },
|
||||
{ "procedure", KeywordType.Procedure },
|
||||
{ "function", KeywordType.Function },
|
||||
{ "begin", KeywordType.Begin },
|
||||
{ "end", KeywordType.End },
|
||||
{ "array", KeywordType.Array },
|
||||
{ "of", KeywordType.Of },
|
||||
{ "if", KeywordType.If },
|
||||
{ "then", KeywordType.Then },
|
||||
{ "else", KeywordType.Else },
|
||||
{ "for", KeywordType.For },
|
||||
{ "to", KeywordType.To },
|
||||
{ "do", KeywordType.Do },
|
||||
{ "integer", KeywordType.Integer },
|
||||
{ "real", KeywordType.Real },
|
||||
{ "boolean", KeywordType.Boolean },
|
||||
{ "character", KeywordType.Character },
|
||||
{ "div", KeywordType.Divide }, // 注意: Pascal 使用 'div' 而不是 '/'
|
||||
{ "not", KeywordType.Not },
|
||||
{ "mod", KeywordType.Mod },
|
||||
{ "and", KeywordType.And },
|
||||
{ "or", KeywordType.Or }
|
||||
};
|
||||
|
||||
public static KeywordType GetKeywordTypeByKeyword(string keyword)
|
||||
{
|
||||
|
@ -199,56 +194,6 @@ public class KeywordSemanticToken : SemanticToken
|
|||
}
|
||||
}
|
||||
|
||||
public static bool TryParse(uint linePos, uint characterPos, LinkedListNode<char> now,
|
||||
out KeywordSemanticToken? token)
|
||||
{
|
||||
string buffer = new([now.Value]);
|
||||
|
||||
if (now.Next is null)
|
||||
{
|
||||
// 没有比两个字符更短的关键字
|
||||
token = null;
|
||||
return false;
|
||||
}
|
||||
|
||||
now = now.Next;
|
||||
buffer += now.Value;
|
||||
|
||||
switch (buffer)
|
||||
{
|
||||
case "do":
|
||||
token = new KeywordSemanticToken
|
||||
{
|
||||
LinePos = linePos,
|
||||
CharacterPos = characterPos,
|
||||
LiteralValue = "do",
|
||||
KeywordType = KeywordType.Do
|
||||
};
|
||||
return true;
|
||||
case "Of":
|
||||
token = new KeywordSemanticToken
|
||||
{
|
||||
LinePos = linePos,
|
||||
CharacterPos = characterPos,
|
||||
LiteralValue = "of",
|
||||
KeywordType = KeywordType.Of
|
||||
};
|
||||
return true;
|
||||
case "If":
|
||||
token = new KeywordSemanticToken
|
||||
{
|
||||
LinePos = linePos,
|
||||
CharacterPos = characterPos,
|
||||
LiteralValue = "if",
|
||||
KeywordType = KeywordType.If
|
||||
};
|
||||
return true;
|
||||
}
|
||||
|
||||
token = null;
|
||||
return false;
|
||||
}
|
||||
|
||||
public override int GetHashCode()
|
||||
{
|
||||
return base.GetHashCode() ^ this.KeywordType.GetHashCode();
|
||||
|
@ -291,16 +236,9 @@ public class OperatorSemanticToken : SemanticToken
|
|||
}
|
||||
}
|
||||
|
||||
public static bool TryParse(uint linePos, uint characterPos, LinkedListNode<char> now,
|
||||
out OperatorSemanticToken? token)
|
||||
{
|
||||
token = null;
|
||||
return false;
|
||||
}
|
||||
|
||||
public override int GetHashCode()
|
||||
{
|
||||
return base.GetHashCode() ^ this.OperatorType.GetHashCode();
|
||||
return base.GetHashCode() ^ OperatorType.GetHashCode();
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -315,7 +253,7 @@ public class NumberSemanticToken : SemanticToken
|
|||
|
||||
public override int GetHashCode()
|
||||
{
|
||||
return base.GetHashCode() ^ this.NumberType.GetHashCode();
|
||||
return base.GetHashCode() ^ NumberType.GetHashCode();
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -326,17 +264,13 @@ public class IdentifierSemanticToken : SemanticToken
|
|||
{
|
||||
public override SemanticTokenType TokenType => SemanticTokenType.Identifier;
|
||||
|
||||
public static bool TryParse(uint linePos, uint characterPos, LinkedListNode<char> now,
|
||||
out IdentifierSemanticToken? token)
|
||||
{
|
||||
token = null;
|
||||
return false;
|
||||
}
|
||||
/// <summary>
|
||||
/// 标识符名称
|
||||
/// </summary>
|
||||
public string IdentifierName => LiteralValue.ToLower();
|
||||
}
|
||||
|
||||
public class EndSemanticToken : SemanticToken
|
||||
{
|
||||
public override SemanticTokenType TokenType => SemanticTokenType.End;
|
||||
}
|
||||
|
||||
|
||||
|
|
|
@ -1,149 +1,16 @@
|
|||
using System.Text.RegularExpressions;
|
||||
using Canon.Core.Enums;
|
||||
using Canon.Core.Enums;
|
||||
using Canon.Core.Exceptions;
|
||||
using Canon.Core.LexicalParser;
|
||||
using Xunit.Abstractions;
|
||||
using Canon.Tests.Utils;
|
||||
using Canon.Core.Abstractions;
|
||||
using Xunit.Abstractions;
|
||||
|
||||
namespace Canon.Tests.LexicalParserTests;
|
||||
|
||||
public class LexicalFileTests
|
||||
public class LexicalFileTests(ITestOutputHelper testOutputHelper)
|
||||
{
|
||||
private readonly ITestOutputHelper _testOutputHelper;
|
||||
private readonly ILexer _lexer = new Lexer();
|
||||
|
||||
public LexicalFileTests(ITestOutputHelper testOutputHelper)
|
||||
{
|
||||
_testOutputHelper = testOutputHelper;
|
||||
}
|
||||
|
||||
//TODO: 基础的字符串匹配,因此变量名称不能被包含。手写一个存在包含情况的测试文件。
|
||||
private static (int, int) FindNthPosition(string pascalProgram, string target, int occurrence)
|
||||
{
|
||||
int lineNumber = 0;
|
||||
(int, int) nthPosition = (0, 0);
|
||||
int foundCount = 0;
|
||||
occurrence = occurrence + 1;
|
||||
|
||||
using (StringReader sr = new StringReader(pascalProgram))
|
||||
{
|
||||
string line;
|
||||
while ((line = sr.ReadLine()) != null)
|
||||
{
|
||||
lineNumber++;
|
||||
int columnNumber = -1;
|
||||
|
||||
// line = Regex.Replace(line, "'[^']*'", "$");
|
||||
|
||||
while ((columnNumber = line.IndexOf(target, columnNumber + 1, StringComparison.Ordinal)) != -1)
|
||||
{
|
||||
foundCount++;
|
||||
if (foundCount == occurrence)
|
||||
{
|
||||
nthPosition = (lineNumber, columnNumber + target.Length);
|
||||
return nthPosition;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (nthPosition == (0, 0))
|
||||
{
|
||||
throw new Exception($"'{target}' not found in program.");
|
||||
}
|
||||
|
||||
return nthPosition;
|
||||
}
|
||||
|
||||
private void TestLexicalAnalysis(string pascalProgram, List<(string, SemanticTokenType, int)> stringLiterals)
|
||||
{
|
||||
var expectedTokens = new List<SemanticToken>();
|
||||
|
||||
foreach (var (literal, tokenType, skipCount) in stringLiterals)
|
||||
{
|
||||
var (line, column) = FindNthPosition(pascalProgram, literal, skipCount);
|
||||
switch (tokenType)
|
||||
{
|
||||
case SemanticTokenType.Keyword:
|
||||
expectedTokens.Add(new KeywordSemanticToken
|
||||
{
|
||||
LinePos = (uint)line,
|
||||
CharacterPos = (uint)column,
|
||||
LiteralValue = literal,
|
||||
KeywordType = KeywordSemanticToken.GetKeywordTypeByKeyword(literal)
|
||||
});
|
||||
break;
|
||||
case SemanticTokenType.Identifier:
|
||||
expectedTokens.Add(new IdentifierSemanticToken
|
||||
{
|
||||
LinePos = (uint)line, CharacterPos = (uint)column, LiteralValue = literal
|
||||
});
|
||||
break;
|
||||
case SemanticTokenType.Delimiter:
|
||||
if (DelimiterSemanticToken.TryParse((uint)line, (uint)column, new LinkedListNode<char>(literal[0]),
|
||||
out var delimiterToken))
|
||||
{
|
||||
if (delimiterToken != null)
|
||||
{
|
||||
expectedTokens.Add(delimiterToken);
|
||||
}
|
||||
}
|
||||
|
||||
break;
|
||||
case SemanticTokenType.Operator:
|
||||
expectedTokens.Add(new OperatorSemanticToken
|
||||
{
|
||||
LinePos = (uint)line,
|
||||
CharacterPos = (uint)column,
|
||||
LiteralValue = literal,
|
||||
OperatorType = OperatorSemanticToken.GetOperatorTypeByOperator(literal)
|
||||
});
|
||||
break;
|
||||
case SemanticTokenType.Character:
|
||||
expectedTokens.Add(new CharacterSemanticToken
|
||||
{
|
||||
LinePos = (uint)line, CharacterPos = (uint)column, LiteralValue = literal
|
||||
});
|
||||
break;
|
||||
case SemanticTokenType.Number:
|
||||
expectedTokens.Add(new NumberSemanticToken
|
||||
{
|
||||
LinePos = (uint)line,
|
||||
CharacterPos = (uint)column,
|
||||
LiteralValue = literal,
|
||||
NumberType = NumberType.Integer
|
||||
});
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
expectedTokens = expectedTokens.OrderBy(token => token.LinePos).ThenBy(token => token.CharacterPos).ToList();
|
||||
expectedTokens = expectedTokens.Select(token =>
|
||||
token is CharacterSemanticToken characterToken && characterToken.LiteralValue == "hello, world!"
|
||||
? new CharacterSemanticToken
|
||||
{
|
||||
LinePos = characterToken.LinePos,
|
||||
CharacterPos = characterToken.CharacterPos + 1,
|
||||
LiteralValue = characterToken.LiteralValue
|
||||
}
|
||||
: token).ToList();
|
||||
|
||||
IEnumerable<SemanticToken> tokensEnumerable = _lexer.Tokenize(new StringSourceReader(pascalProgram));
|
||||
List<SemanticToken> tokens = tokensEnumerable.ToList();
|
||||
|
||||
var actualTokens = tokens;
|
||||
for (int i = 0; i < expectedTokens.Count; i++)
|
||||
{
|
||||
_testOutputHelper.WriteLine($"Expect: {expectedTokens[i]}");
|
||||
_testOutputHelper.WriteLine($"Actual: {actualTokens[i]}");
|
||||
_testOutputHelper.WriteLine("----");
|
||||
// Assert.Equal(expectedTokens[i], actualTokens[i]);
|
||||
}
|
||||
|
||||
Assert.Equal(expectedTokens, actualTokens);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void TestLexicalAnalysisFirst()
|
||||
{
|
||||
|
@ -157,30 +24,30 @@ public class LexicalFileTests
|
|||
end.
|
||||
""";
|
||||
|
||||
var stringLiterals = new List<(string, SemanticTokenType, int)>
|
||||
{
|
||||
("program", SemanticTokenType.Keyword, 0),
|
||||
("HelloWorld", SemanticTokenType.Identifier, 0),
|
||||
(";", SemanticTokenType.Delimiter, 0),
|
||||
("var", SemanticTokenType.Keyword, 0),
|
||||
("message", SemanticTokenType.Identifier, 0),
|
||||
(":", SemanticTokenType.Delimiter, 0),
|
||||
("string", SemanticTokenType.Identifier, 0),
|
||||
(";", SemanticTokenType.Delimiter, 1),
|
||||
("begin", SemanticTokenType.Keyword, 0),
|
||||
("message", SemanticTokenType.Identifier, 1),
|
||||
(":=", SemanticTokenType.Operator, 0),
|
||||
("hello, world!", SemanticTokenType.Character, 0),
|
||||
(";", SemanticTokenType.Delimiter, 2),
|
||||
("writeln", SemanticTokenType.Identifier, 0),
|
||||
("(", SemanticTokenType.Delimiter, 0),
|
||||
("message", SemanticTokenType.Identifier, 2),
|
||||
(")", SemanticTokenType.Delimiter, 0),
|
||||
(";", SemanticTokenType.Delimiter, 3),
|
||||
("end", SemanticTokenType.Keyword, 0),
|
||||
(".", SemanticTokenType.Delimiter, 0)
|
||||
};
|
||||
TestLexicalAnalysis(pascalProgram, stringLiterals);
|
||||
IEnumerable<SemanticToken> tokens = _lexer.Tokenize(new StringSourceReader(pascalProgram));
|
||||
ValidateSemanticTokens(tokens, [
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Character,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.End
|
||||
]);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
|
@ -196,30 +63,30 @@ public class LexicalFileTests
|
|||
end.
|
||||
""";
|
||||
|
||||
var stringLiterals = new List<(string, SemanticTokenType, int)>
|
||||
{
|
||||
("program", SemanticTokenType.Keyword, 0),
|
||||
("main", SemanticTokenType.Identifier, 0),
|
||||
(";", SemanticTokenType.Delimiter, 0),
|
||||
("var", SemanticTokenType.Keyword, 0),
|
||||
("ab", SemanticTokenType.Identifier, 0),
|
||||
(":", SemanticTokenType.Delimiter, 0),
|
||||
("integer", SemanticTokenType.Keyword, 0),
|
||||
(";", SemanticTokenType.Delimiter, 1),
|
||||
("begin", SemanticTokenType.Keyword, 0),
|
||||
("ab", SemanticTokenType.Identifier, 1),
|
||||
(":=", SemanticTokenType.Operator, 0),
|
||||
("3", SemanticTokenType.Number, 0),
|
||||
(";", SemanticTokenType.Delimiter, 2),
|
||||
("write", SemanticTokenType.Identifier, 0),
|
||||
("(", SemanticTokenType.Delimiter, 0),
|
||||
("ab", SemanticTokenType.Identifier, 2),
|
||||
(")", SemanticTokenType.Delimiter, 0),
|
||||
(";", SemanticTokenType.Delimiter, 3),
|
||||
("end", SemanticTokenType.Keyword, 0),
|
||||
(".", SemanticTokenType.Delimiter, 0)
|
||||
};
|
||||
TestLexicalAnalysis(pascalProgram, stringLiterals);
|
||||
IEnumerable<SemanticToken> tokens = _lexer.Tokenize(new StringSourceReader(pascalProgram));
|
||||
|
||||
ValidateSemanticTokens(tokens, [
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Number,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter
|
||||
]);
|
||||
}
|
||||
|
||||
//带注释的测试
|
||||
|
@ -239,42 +106,74 @@ public class LexicalFileTests
|
|||
end.
|
||||
""";
|
||||
|
||||
var stringLiterals = new List<(string, SemanticTokenType, int)>
|
||||
{
|
||||
("program", SemanticTokenType.Keyword, 0),
|
||||
("main", SemanticTokenType.Identifier, 0),
|
||||
(";", SemanticTokenType.Delimiter, 0),
|
||||
("var", SemanticTokenType.Keyword, 0),
|
||||
("ab", SemanticTokenType.Identifier, 0),
|
||||
(",", SemanticTokenType.Delimiter, 0),
|
||||
("ba", SemanticTokenType.Identifier, 0),
|
||||
(":", SemanticTokenType.Delimiter, 0),
|
||||
("integer", SemanticTokenType.Keyword, 0),
|
||||
(";", SemanticTokenType.Delimiter, 1),
|
||||
("begin", SemanticTokenType.Keyword, 0),
|
||||
("ab", SemanticTokenType.Identifier, 1),
|
||||
(":=", SemanticTokenType.Operator, 0),
|
||||
("3", SemanticTokenType.Number, 0),
|
||||
(";", SemanticTokenType.Delimiter, 2),
|
||||
("ba", SemanticTokenType.Identifier, 1),
|
||||
(":=", SemanticTokenType.Operator, 1),
|
||||
("5", SemanticTokenType.Number, 0),
|
||||
(";", SemanticTokenType.Delimiter, 3),
|
||||
("ab", SemanticTokenType.Identifier, 2),
|
||||
(":=", SemanticTokenType.Operator, 2),
|
||||
("5", SemanticTokenType.Number, 1),
|
||||
(";", SemanticTokenType.Delimiter, 4),
|
||||
("write", SemanticTokenType.Identifier, 0),
|
||||
("(", SemanticTokenType.Delimiter, 0),
|
||||
("ab", SemanticTokenType.Identifier, 3),
|
||||
("+", SemanticTokenType.Operator, 0),
|
||||
("ba", SemanticTokenType.Identifier, 2),
|
||||
(")", SemanticTokenType.Delimiter, 0),
|
||||
(";", SemanticTokenType.Delimiter, 5),
|
||||
("end", SemanticTokenType.Keyword, 0),
|
||||
(".", SemanticTokenType.Delimiter, 0)
|
||||
};
|
||||
TestLexicalAnalysis(pascalProgram, stringLiterals);
|
||||
IEnumerable<SemanticToken> tokens = _lexer.Tokenize(new StringSourceReader(pascalProgram));
|
||||
|
||||
ValidateSemanticTokens(tokens, [
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Number,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Number,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Number,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Operator,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.End
|
||||
]);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void ReuseTest()
|
||||
{
|
||||
const string program1 = """
|
||||
program main;
|
||||
begin
|
||||
end.
|
||||
""";
|
||||
IEnumerable<SemanticToken> tokens = _lexer.Tokenize(new StringSourceReader(program1));
|
||||
|
||||
ValidateSemanticTokens(tokens, [
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Identifier,
|
||||
SemanticTokenType.Delimiter,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter
|
||||
]);
|
||||
|
||||
const string test = "program begin end.";
|
||||
|
||||
tokens = _lexer.Tokenize(new StringSourceReader(test));
|
||||
|
||||
ValidateSemanticTokens(tokens, [
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Keyword,
|
||||
SemanticTokenType.Delimiter
|
||||
]);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
|
@ -291,7 +190,7 @@ public class LexicalFileTests
|
|||
""";
|
||||
var ex = Assert.Throws<LexemeException>(() => _lexer.Tokenize(new StringSourceReader(pascalProgram)).ToList());
|
||||
//打印exception信息
|
||||
_testOutputHelper.WriteLine(ex.ToString());
|
||||
testOutputHelper.WriteLine(ex.ToString());
|
||||
Assert.Equal(LexemeErrorType.UnclosedComment, ex.ErrorType);
|
||||
Assert.Equal((uint)7, ex.Line);
|
||||
Assert.Equal((uint)5, ex.CharPosition);
|
||||
|
@ -307,7 +206,7 @@ public class LexicalFileTests
|
|||
program CommentNotClosed;
|
||||
""";
|
||||
var ex = Assert.Throws<LexemeException>(() => _lexer.Tokenize(new StringSourceReader(pascalProgram)).ToList());
|
||||
_testOutputHelper.WriteLine(ex.ToString());
|
||||
testOutputHelper.WriteLine(ex.ToString());
|
||||
Assert.Equal(LexemeErrorType.UnclosedComment, ex.ErrorType);
|
||||
Assert.Equal((uint)4, ex.Line);
|
||||
Assert.Equal((uint)26, ex.CharPosition);
|
||||
|
@ -410,4 +309,13 @@ public class LexicalFileTests
|
|||
List<SemanticToken> tokens = tokensEnumerable.ToList();
|
||||
Assert.NotNull(tokens);
|
||||
}
|
||||
|
||||
private static void ValidateSemanticTokens(IEnumerable<SemanticToken> actualTokens,
|
||||
IEnumerable<SemanticTokenType> expectedTypes)
|
||||
{
|
||||
foreach ((SemanticTokenType type, SemanticToken token) in expectedTypes.Zip(actualTokens))
|
||||
{
|
||||
Assert.Equal(type, token.TokenType);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue
Block a user