This repository has been archived on 2024-02-27. You can view files and clone it, but cannot push or open issues or pull requests.
arf/lexer/lexer.go

199 lines
4.0 KiB
Go
Raw Normal View History

2022-08-07 13:18:59 -06:00
package lexer
2022-08-09 18:45:06 -06:00
import "io"
import "github.com/sashakoshka/arf/file"
2022-08-07 13:18:59 -06:00
// LexingOperation holds information about an ongoing lexing operataion.
type LexingOperation struct {
file *file.File
char rune
tokens []Token
2022-08-07 13:18:59 -06:00
}
2022-08-09 18:45:06 -06:00
// Tokenize converts a file into a slice of tokens (lexemes).
func Tokenize (file *file.File) (tokens []Token, err error) {
lexer := LexingOperation { file: file }
err = lexer.tokenize()
tokens = lexer.tokens
2022-08-09 18:45:06 -06:00
// if the lexing operation returned io.EOF, nothing went wrong so we
// return nil for err.
if err == io.EOF {
err = nil
}
return
}
// tokenize converts a file into a slice of tokens (lexemes). It will always
// return a non-nil error, but if nothing went wrong it will return io.EOF.
func (lexer *LexingOperation) tokenize () (err error) {
2022-08-09 18:45:06 -06:00
err = lexer.nextRune()
if err != nil { return }
for {
lowercase := lexer.char >= 'a' && lexer.char <= 'z'
uppercase := lexer.char >= 'A' && lexer.char <= 'Z'
number := lexer.char >= '0' && lexer.char <= '9'
if number {
2022-08-09 22:48:18 -06:00
// TODO: tokenize number begin
2022-08-09 18:45:06 -06:00
} else if lowercase || uppercase {
2022-08-09 22:48:18 -06:00
// TODO: tokenize alpha begin
2022-08-09 18:45:06 -06:00
} else {
2022-08-09 20:18:12 -06:00
err = lexer.tokenizeSymbolBeginning()
if err != nil { return err }
2022-08-09 18:45:06 -06:00
}
// TODO: skip whitespace
2022-08-09 18:45:06 -06:00
}
return
2022-08-07 13:18:59 -06:00
}
2022-08-09 20:18:12 -06:00
func (lexer *LexingOperation) tokenizeSymbolBeginning () (err error) {
switch lexer.char {
2022-08-09 23:03:59 -06:00
case '#':
// comment
for lexer.char != '\n' {
lexer.nextRune()
}
2022-08-09 20:18:12 -06:00
case '\t':
2022-08-09 23:03:59 -06:00
// indent level
previousToken := lexer.tokens[len(lexer.tokens) - 1]
if !previousToken.Is(TokenKindNewline) ||
!previousToken.Is(TokenKindNewline) {
file.NewError (
lexer.file.Location(), 1,
"tab not used as indent",
file.ErrorKindWarn)
break
}
2022-08-09 20:18:12 -06:00
for lexer.char == '\t' {
lexer.addToken (Token {
kind: TokenKindIndent,
})
lexer.nextRune()
}
2022-08-09 23:03:59 -06:00
case '\n':
// line break
2022-08-10 09:28:29 -06:00
// TODO: if last line was blank, (ony whitespace) discard.
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindNewline,
})
lexer.nextRune()
2022-08-09 20:18:12 -06:00
case '"':
// TODO: tokenize string literal
lexer.nextRune()
case '\'':
// TODO: tokenize rune literal
lexer.nextRune()
case ':':
lexer.addToken (Token {
kind: TokenKindColon,
})
lexer.nextRune()
case '.':
lexer.addToken (Token {
kind: TokenKindDot,
})
lexer.nextRune()
case '[':
lexer.addToken (Token {
kind: TokenKindLBracket,
})
lexer.nextRune()
case ']':
lexer.addToken (Token {
kind: TokenKindRBracket,
})
lexer.nextRune()
case '{':
lexer.addToken (Token {
kind: TokenKindLBrace,
})
lexer.nextRune()
case '}':
lexer.addToken (Token {
kind: TokenKindRBrace,
})
lexer.nextRune()
2022-08-09 22:48:18 -06:00
case '+':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindPlus,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '-':
// TODO: tokenize dash begin
lexer.nextRune()
case '*':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindAsterisk,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '/':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindSlash,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '@':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindAt,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '!':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindExclamation,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '%':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindPercent,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '~':
2022-08-09 23:03:59 -06:00
lexer.addToken (Token {
kind: TokenKindTilde,
})
2022-08-09 22:48:18 -06:00
lexer.nextRune()
case '<':
// TODO: tokenize less than begin
lexer.nextRune()
case '>':
// TODO: tokenize greater than begin
lexer.nextRune()
case '|':
// TODO: tokenize bar begin
lexer.nextRune()
case '&':
// TODO: tokenize and begin
lexer.nextRune()
2022-08-09 20:18:12 -06:00
default:
err = file.NewError (
lexer.file.Location(), 1,
"unexpected character " +
string(lexer.char),
file.ErrorKindError)
return
}
return
}
func (lexer *LexingOperation) addToken (token Token) {
lexer.tokens = append(lexer.tokens, token)
}
2022-08-09 18:45:06 -06:00
// nextRune advances the lexer to the next rune in the file.
func (lexer *LexingOperation) nextRune () (err error) {
lexer.char, _, err = lexer.file.ReadRune()
if err != nil && err != io.EOF {
return file.NewError (
lexer.file.Location(), 1,
err.Error(), file.ErrorKindError)
}
2022-08-07 13:18:59 -06:00
return
}