Pasha/LXC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added symbols/operators to lexer

Browse Source
This commit is contained in:
Pasha Bibko
2025-07-21 17:34:47 +01:00
parent a6afeff493
commit 24fde1b770
6 changed files with 158 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Common/File.h
View File

@@ -75,14 +75,14 @@ namespace LXC::Util
// Finds the location of a given index within a file //
inline bool GetFileLocationAtIndex(FileLocation& location, const std::string& file, __int32 index)
{
// Returns false if outside the bounds //
if (index < 0 || index > file.length())
return false;
// Resets location //
location.line = 1;
location.col = 1;
// Returns false if outside the bounds //
if (index < 0 || index > file.length())
return false;
// Finds the location //
__int32 localIndex = 0;
while (localIndex != index)

1
Common/LXC.h
View File

@@ -2,6 +2,7 @@
// Standard libraries //
#include <unordered_map>
#include <vector>
// LXC util files //

3
LXC/LXC.cpp
View File

@@ -47,6 +47,9 @@ int main(int argc, char** argv)
if (err.reason == Lexer::LexerError::InvalidCharacter)
Util::PrintLn(": {", fileContents.Result()[err.index], '}');
if (err.reason == Lexer::LexerError::UnknownSymbolOrOperand)
Util::PrintLn(": {", err.info, '}');
else
Util::PrintLn();

11
Lexer/inc/Lexer.h
View File

@@ -27,12 +27,13 @@ namespace LXC::Lexer
enum Reason
{
InvalidCharacter,
UnterminatedStringLiteral
UnterminatedStringLiteral,
UnknownSymbolOrOperand
};
// Constructor to pass arguments through to the struct //
LexerError(Reason _reason, __int32 errorIndex)
: reason(_reason), index(errorIndex)
LexerError(Reason _reason, __int32 errorIndex, std::string _info = "")
: reason(_reason), index(errorIndex), info(_info)
{}
// Turns the error into a c-string //
@@ -41,7 +42,8 @@ namespace LXC::Lexer
static const char* reasons[] =
{
"Invalid character found in source",
"Unterminated string literal in source"
"Unterminated string literal in source",
"Unknown symbol or operand in source"
};
return reasons[reason];
@@ -50,6 +52,7 @@ namespace LXC::Lexer
// Error information //
const Reason reason;
const __int32 index;
const std::string info;
};
// Turns a file into a vector of tokens //

229
Lexer/src/Lexer.cpp
View File

@@ -5,116 +5,171 @@
namespace LXC::Internal
{
static constexpr bool IsNumeric(const char c)
{
return c >= '0' && c <= '9';
}
static constexpr bool IsNumeric(const char c)
{
return c >= '0' && c <= '9';
}
static constexpr bool IsAlpha(const char c)
{
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
}
static constexpr bool IsAlpha(const char c)
{
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
}
static constexpr bool IsWhitespace(const char c)
{
return c == ' ' || c == '\t' || c == '\n' || c == '\r';
}
static constexpr bool IsWhitespace(const char c)
{
return c == ' ' || c == '\t' || c == '\n' || c == '\r';
}
static constexpr bool IsSymbolOrOperator(const char c)
{
return
c == '+' || c == '-' ||
c == '*' || c == '/' ||
c == '%' || c == '=' ||
c == ',' || c == '[' ||
c == ']' || c == '{' ||
c == '}' || c == '(' ||
c == ')';
}
static const std::unordered_map<std::string_view, Lexer::Token::TokenType> symbolAndOpMap =
{
{ "+", Lexer::Token::Add },
{ "-", Lexer::Token::Sub },
{ "*", Lexer::Token::Mul },
{ "/", Lexer::Token::Div },
{ "%", Lexer::Token::Mod },
{ "=", Lexer::Token::Assign },
{ ",", Lexer::Token::Comma },
{ "[", Lexer::Token::CloseBracket },
{ "]", Lexer::Token::OpenBracket },
{ "{", Lexer::Token::CloseBrace },
{ "}", Lexer::Token::OpenBrace },
{ ")", Lexer::Token::CloseParen },
{ "(", Lexer::Token::OpenParen }
};
}
namespace LXC::Lexer
{
LexerContext::LexerContext(const std::string& _source) :
source(_source), index(0), out{}, len((__int32)_source.length()), column(0), line(0)
{}
LexerContext::LexerContext(const std::string& _source) :
source(_source), index(0), out{}, len((__int32)_source.length()), column(0), line(0)
{}
Util::ReturnVal<LexerOutput, LexerError> TokenizeFile(const std::string& fileContents)
{
// Creates the context for the lexer //
LexerContext ctx(fileContents);
Util::ReturnVal<LexerOutput, LexerError> TokenizeFile(const std::string& fileContents)
{
// Creates the context for the lexer //
LexerContext ctx(fileContents);
struct
{
bool inStrLiteral = false;
bool inIdentifier = false;
bool inNumLiteral = false;
struct
{
bool inStrLiteral = false;
bool inIdentifier = false;
bool inNumLiteral = false;
bool inSymbolOrOp = false;
bool inComment = false;
bool inComment = false;
unsigned __int32 sectionStart = 0;
unsigned __int32 sectionStart = 0;
} trackers;
} trackers;
while (ctx.index < ctx.len)
{
// The current char within the source that is being lexed //
const char current = ctx.source[ctx.index];
const char next = (ctx.index + 1 < ctx.len) ? ctx.source[ctx.index + 1] : '\0';
while (ctx.index < ctx.len)
{
// The current char within the source that is being lexed //
const char current = ctx.source[ctx.index];
const char next = (ctx.index + 1 < ctx.len) ? ctx.source[ctx.index + 1] : '\0';
// === Comments === //
if (current == '#')
trackers.inComment = !trackers.inComment;
// === Comments === //
if (current == '#')
trackers.inComment = !trackers.inComment;
else if (trackers.inComment) {} // Contents of comments are skipped over
else if (trackers.inComment) {} // Contents of comments are skipped over
// === String literals === //
else if (current == '"')
{
// Updates trackers //
trackers.inStrLiteral = !trackers.inStrLiteral;
trackers.sectionStart = trackers.inStrLiteral ? ctx.index : trackers.sectionStart;
// === String literals === //
else if (current == '"')
{
// Updates trackers //
trackers.inStrLiteral = !trackers.inStrLiteral;
trackers.sectionStart = trackers.inStrLiteral ? ctx.index : trackers.sectionStart;
// Creates the token (if at the end of the string literal) //
if (!trackers.inStrLiteral)
ctx.out.emplace_back(ctx, trackers.sectionStart + 1, (USHORT)(ctx.index - trackers.sectionStart - 1), Token::StringLiteral);
} else if (trackers.inStrLiteral) {}
// Creates the token (if at the end of the string literal) //
if (!trackers.inStrLiteral)
ctx.out.emplace_back(ctx, trackers.sectionStart + 1, (USHORT)(ctx.index - trackers.sectionStart - 1), Token::StringLiteral);
} else if (trackers.inStrLiteral) {}
// === Numbers === //
else if (Internal::IsNumeric(current))
{
// Updates trackers //
trackers.sectionStart = trackers.inNumLiteral ? trackers.sectionStart : ctx.index;
trackers.inNumLiteral = true;
// === Numbers === //
else if (Internal::IsNumeric(current))
{
// Updates trackers //
trackers.sectionStart = trackers.inNumLiteral ? trackers.sectionStart : ctx.index;
trackers.inNumLiteral = true;
// Checks for the end of the number literal to create the token //
if (!Internal::IsNumeric(next)) _UNLIKELY
{
ctx.out.emplace_back(ctx, trackers.sectionStart, (USHORT)(ctx.index - trackers.sectionStart + 1), Token::NumLiteral);
trackers.inNumLiteral = false;
}
}
// Checks for the end of the number literal to create the token //
if (!Internal::IsNumeric(next)) _UNLIKELY
{
ctx.out.emplace_back(ctx, trackers.sectionStart, (USHORT)(ctx.index - trackers.sectionStart + 1), Token::NumLiteral);
trackers.inNumLiteral = false;
}
}
// === Words === //
else if (Internal::IsAlpha(current))
{
// Updates trackers //
trackers.sectionStart = trackers.inIdentifier ? trackers.sectionStart : ctx.index;
trackers.inIdentifier = true;
// === Words === //
else if (Internal::IsAlpha(current))
{
// Updates trackers //
trackers.sectionStart = trackers.inIdentifier ? trackers.sectionStart : ctx.index;
trackers.inIdentifier = true;
// Checks for the end of the word to create the token //
if (!Internal::IsAlpha(next)) _UNLIKELY
{
ctx.out.emplace_back(ctx, trackers.sectionStart, (USHORT)(ctx.index - trackers.sectionStart + 1), Token::Identifier);
trackers.inIdentifier = false;
}
}
// Checks for the end of the word to create the token //
if (!Internal::IsAlpha(next)) _UNLIKELY
{
ctx.out.emplace_back(ctx, trackers.sectionStart, (USHORT)(ctx.index - trackers.sectionStart + 1), Token::Identifier);
trackers.inIdentifier = false;
}
}
// === Whitespace === //
else if (Internal::IsWhitespace(current)) {}
// === Symbols/Operators === //
else if (Internal::IsSymbolOrOperator(current))
{
// Updates trackers //
trackers.sectionStart = trackers.inSymbolOrOp ? trackers.sectionStart : ctx.index;
trackers.inSymbolOrOp = true;
// If an if-statement has not been triggered the character must be invalid //
else
return Util::FunctionFail<LexerError>(LexerError::InvalidCharacter, ctx.index);
// Checks for the end of the symbol or operator //
if (!Internal::IsSymbolOrOperator(next))
{
// Finds the operator/symbol if it can //
std::string_view fullSymbol(ctx.source.data() + trackers.sectionStart, ctx.index - trackers.sectionStart + 1);
auto it = Internal::symbolAndOpMap.find(fullSymbol);
if (it != Internal::symbolAndOpMap.end())
ctx.out.emplace_back(ctx, trackers.sectionStart, (USHORT)(ctx.index - trackers.sectionStart + 1), it->second);
// Iterates to the next index //
ctx.column++;
ctx.index++;
}
else
return Util::FunctionFail<LexerError>(LexerError::UnknownSymbolOrOperand, trackers.sectionStart, std::string(fullSymbol));
}
}
// Checks for an unterminated string literal //
if (trackers.inStrLiteral)
return Util::FunctionFail<LexerError>(LexerError::UnterminatedStringLiteral, trackers.sectionStart);
// === Whitespace === //
else if (Internal::IsWhitespace(current)) {}
return ctx.out;
}
// If an if-statement has not been triggered the character must be invalid //
else
return Util::FunctionFail<LexerError>(LexerError::InvalidCharacter, ctx.index);
// Iterates to the next index //
ctx.column++;
ctx.index++;
}
// Checks for an unterminated string literal //
if (trackers.inStrLiteral)
return Util::FunctionFail<LexerError>(LexerError::UnterminatedStringLiteral, trackers.sectionStart);
return ctx.out;
}
}

2
example/example.lx
View File

@@ -1 +1 @@
FILE 4 CONTENTS "A" GO B HERE 34 5 "ELLO THER"
FILE 4 CONTENTS "A" GO B HERE 34 += 5 "ELLO THER"