From ac2e5a082d8226d50171534ab7126b1df077169c Mon Sep 17 00:00:00 2001 From: oabrivard Date: Mon, 28 Aug 2023 09:44:49 +0200 Subject: [PATCH] Completed chapter 1 on Lexers --- monkey1/go.mod | 3 + monkey1/lexer/lexer.go | 137 ++++++++++++++++++++++++++++++++++++ monkey1/lexer/lexer_test.go | 126 +++++++++++++++++++++++++++++++++ monkey1/main.go | 20 ++++++ monkey1/repl/repl.go | 31 ++++++++ monkey1/token/token.go | 66 +++++++++++++++++ 6 files changed, 383 insertions(+) create mode 100644 monkey1/go.mod create mode 100644 monkey1/lexer/lexer.go create mode 100644 monkey1/lexer/lexer_test.go create mode 100644 monkey1/main.go create mode 100644 monkey1/repl/repl.go create mode 100644 monkey1/token/token.go diff --git a/monkey1/go.mod b/monkey1/go.mod new file mode 100644 index 0000000..01b6f07 --- /dev/null +++ b/monkey1/go.mod @@ -0,0 +1,3 @@ +module gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1 + +go 1.21.0 diff --git a/monkey1/lexer/lexer.go b/monkey1/lexer/lexer.go new file mode 100644 index 0000000..3613013 --- /dev/null +++ b/monkey1/lexer/lexer.go @@ -0,0 +1,137 @@ +package lexer + +import "gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1/token" + +type Lexer struct { + input string + position int // current position in input (points to current char) + readPosition int // current reading position in input (after current char) + ch byte // current char under examination +} + +func New(input string) *Lexer { + l := &Lexer{input: input} + l.readChar() + return l +} + +func (l *Lexer) NextToken() token.Token { + var tok token.Token + + l.skipWhitespace() + + switch l.ch { + case '=': + if l.peekChar() == '=' { + ch := l.ch + l.readChar() + literal := string(ch) + string(l.ch) + tok = token.Token{Type: token.EQ, Literal: literal} + } else { + tok = newToken(token.ASSIGN, l.ch) + } + case '+': + tok = newToken(token.PLUS, l.ch) + case '-': + tok = newToken(token.MINUS, l.ch) + case '!': + if l.peekChar() == '=' { + ch := l.ch + l.readChar() + literal := string(ch) + string(l.ch) + tok = token.Token{Type: token.NOT_EQ, Literal: literal} + } else { + tok = newToken(token.BANG, l.ch) + } + case '/': + tok = newToken(token.SLASH, l.ch) + case '*': + tok = newToken(token.ASTERISK, l.ch) + case '<': + tok = newToken(token.LT, l.ch) + case '>': + tok = newToken(token.GT, l.ch) + case ';': + tok = newToken(token.SEMICOLON, l.ch) + case ',': + tok = newToken(token.COMMA, l.ch) + case '{': + tok = newToken(token.LBRACE, l.ch) + case '}': + tok = newToken(token.RBRACE, l.ch) + case '(': + tok = newToken(token.LPAREN, l.ch) + case ')': + tok = newToken(token.RPAREN, l.ch) + case 0: + tok.Literal = "" + tok.Type = token.EOF + default: + if isLetter(l.ch) { + tok.Literal = l.readIdentifier() + tok.Type = token.LookupIdent(tok.Literal) + return tok + } else if isDigit(l.ch) { + tok.Type = token.INT + tok.Literal = l.readNumber() + return tok + } else { + tok = newToken(token.ILLEGAL, l.ch) + } + } + + l.readChar() + return tok +} + +func (l *Lexer) skipWhitespace() { + for l.ch == ' ' || l.ch == '\t' || l.ch == '\n' || l.ch == '\r' { + l.readChar() + } +} + +func (l *Lexer) readChar() { + if l.readPosition >= len(l.input) { + l.ch = 0 + } else { + l.ch = l.input[l.readPosition] + } + l.position = l.readPosition + l.readPosition += 1 +} + +func (l *Lexer) peekChar() byte { + if l.readPosition >= len(l.input) { + return 0 + } else { + return l.input[l.readPosition] + } +} + +func (l *Lexer) readIdentifier() string { + position := l.position + for isLetter(l.ch) { + l.readChar() + } + return l.input[position:l.position] +} + +func (l *Lexer) readNumber() string { + position := l.position + for isDigit(l.ch) { + l.readChar() + } + return l.input[position:l.position] +} + +func isLetter(ch byte) bool { + return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch == '_' +} + +func isDigit(ch byte) bool { + return '0' <= ch && ch <= '9' +} + +func newToken(tokenType token.TokenType, ch byte) token.Token { + return token.Token{Type: tokenType, Literal: string(ch)} +} diff --git a/monkey1/lexer/lexer_test.go b/monkey1/lexer/lexer_test.go new file mode 100644 index 0000000..17d1aca --- /dev/null +++ b/monkey1/lexer/lexer_test.go @@ -0,0 +1,126 @@ +package lexer + +import ( + "testing" + + "gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1/token" +) + +func TestNextToken(t *testing.T) { + input := `let five = 5; +let ten = 10; + +let add = fn(x, y) { + x + y; +}; + +let result = add(five, ten); +!-/*5; +5 < 10 > 5; + +if (5 < 10) { + return true; +} else { + return false; +} + +10 == 10; +10 != 9; +` + + tests := []struct { + expectedType token.TokenType + expectedLiteral string + }{ + {token.LET, "let"}, + {token.IDENT, "five"}, + {token.ASSIGN, "="}, + {token.INT, "5"}, + {token.SEMICOLON, ";"}, + {token.LET, "let"}, + {token.IDENT, "ten"}, + {token.ASSIGN, "="}, + {token.INT, "10"}, + {token.SEMICOLON, ";"}, + {token.LET, "let"}, + {token.IDENT, "add"}, + {token.ASSIGN, "="}, + {token.FUNCTION, "fn"}, + {token.LPAREN, "("}, + {token.IDENT, "x"}, + {token.COMMA, ","}, + {token.IDENT, "y"}, + {token.RPAREN, ")"}, + {token.LBRACE, "{"}, + {token.IDENT, "x"}, + {token.PLUS, "+"}, + {token.IDENT, "y"}, + {token.SEMICOLON, ";"}, + {token.RBRACE, "}"}, + {token.SEMICOLON, ";"}, + {token.LET, "let"}, + {token.IDENT, "result"}, + {token.ASSIGN, "="}, + {token.IDENT, "add"}, + {token.LPAREN, "("}, + {token.IDENT, "five"}, + {token.COMMA, ","}, + {token.IDENT, "ten"}, + {token.RPAREN, ")"}, + {token.SEMICOLON, ";"}, + {token.BANG, "!"}, + {token.MINUS, "-"}, + {token.SLASH, "/"}, + {token.ASTERISK, "*"}, + {token.INT, "5"}, + {token.SEMICOLON, ";"}, + {token.INT, "5"}, + {token.LT, "<"}, + {token.INT, "10"}, + {token.GT, ">"}, + {token.INT, "5"}, + {token.SEMICOLON, ";"}, + {token.IF, "if"}, + {token.LPAREN, "("}, + {token.INT, "5"}, + {token.LT, "<"}, + {token.INT, "10"}, + {token.RPAREN, ")"}, + {token.LBRACE, "{"}, + {token.RETURN, "return"}, + {token.TRUE, "true"}, + {token.SEMICOLON, ";"}, + {token.RBRACE, "}"}, + {token.ELSE, "else"}, + {token.LBRACE, "{"}, + {token.RETURN, "return"}, + {token.FALSE, "false"}, + {token.SEMICOLON, ";"}, + {token.RBRACE, "}"}, + {token.INT, "10"}, + {token.EQ, "=="}, + {token.INT, "10"}, + {token.SEMICOLON, ";"}, + {token.INT, "10"}, + {token.NOT_EQ, "!="}, + {token.INT, "9"}, + {token.SEMICOLON, ";"}, + {token.EOF, ""}, + } + + l := New(input) + + for i, tt := range tests { + tok := l.NextToken() + + if tok.Type != tt.expectedType { + t.Fatalf("tests[%d] - tokentype wrong. expected=%q, got=%q", + i, tt.expectedType, tok.Type) + } + + if tok.Literal != tt.expectedLiteral { + t.Fatalf("tests[%d] - literal wrong. expected=%q, got=%q", + i, tt.expectedLiteral, tok.Literal) + } + } +} diff --git a/monkey1/main.go b/monkey1/main.go new file mode 100644 index 0000000..8928430 --- /dev/null +++ b/monkey1/main.go @@ -0,0 +1,20 @@ +package main + +import ( + "fmt" + "os" + "os/user" + + "gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1/repl" +) + +func main() { + user, err := user.Current() + if err != nil { + panic(err) + } + fmt.Printf("Hello %s! This is the Monkey programming language!\n", + user.Username) + fmt.Printf("Feel free to type in commands\n") + repl.Start(os.Stdin, os.Stdout) +} diff --git a/monkey1/repl/repl.go b/monkey1/repl/repl.go new file mode 100644 index 0000000..d55a492 --- /dev/null +++ b/monkey1/repl/repl.go @@ -0,0 +1,31 @@ +package repl + +import ( + "bufio" + "fmt" + "io" + + "gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1/lexer" + "gitea.paas.celticinfo.fr/oabrivard/monkeylang/monkey1/token" +) + +const PROMPT = ">> " + +func Start(in io.Reader, out io.Writer) { + scanner := bufio.NewScanner(in) + + for { + fmt.Printf(PROMPT) + scanned := scanner.Scan() + if !scanned { + return + } + + line := scanner.Text() + l := lexer.New(line) + + for tok := l.NextToken(); tok.Type != token.EOF; tok = l.NextToken() { + fmt.Printf("%+v\n", tok) + } + } +} diff --git a/monkey1/token/token.go b/monkey1/token/token.go new file mode 100644 index 0000000..12158fa --- /dev/null +++ b/monkey1/token/token.go @@ -0,0 +1,66 @@ +package token + +type TokenType string + +const ( + ILLEGAL = "ILLEGAL" + EOF = "EOF" + + // Identifiers + literals + IDENT = "IDENT" // add, foobar, x, y, ... + INT = "INT" // 1343456 + + // Operators + ASSIGN = "=" + PLUS = "+" + MINUS = "-" + BANG = "!" + ASTERISK = "*" + SLASH = "/" + + LT = "<" + GT = ">" + + EQ = "==" + NOT_EQ = "!=" + + // Delimiters + COMMA = "," + SEMICOLON = ";" + + LPAREN = "(" + RPAREN = ")" + LBRACE = "{" + RBRACE = "}" + + // Keywords + FUNCTION = "FUNCTION" + LET = "LET" + TRUE = "TRUE" + FALSE = "FALSE" + IF = "IF" + ELSE = "ELSE" + RETURN = "RETURN" +) + +type Token struct { + Type TokenType + Literal string +} + +var keywords = map[string]TokenType{ + "fn": FUNCTION, + "let": LET, + "true": TRUE, + "false": FALSE, + "if": IF, + "else": ELSE, + "return": RETURN, +} + +func LookupIdent(ident string) TokenType { + if tok, ok := keywords[ident]; ok { + return tok + } + return IDENT +}