《用Go语言自制解释器》之第1章 词法分析

378287007
222 阅读4分钟

第1章 词法分析

1.1 词法分析

源代码 ->（词法分析） 词法单元 ->（语法分析） 抽象语法树

1.2 定义词法单元

//token/token.go
package token

type TokenType string

type Token struct {
	Type TokenType
	Literal string
}

const (
	ILLEGAL = "ILLEGAL" //未知词法单元
	EOF     = "EOF" //文件结尾

	// 标识符+字面量
	IDENT  = "IDENT"  // add, foobar, x, y, ...
	INT    = "INT"    // 1343456
	STRING = "STRING" // "foobar"

	// 运算符
	ASSIGN   = "="
	PLUS     = "+"
	MINUS    = "-"
	BANG     = "!"
	ASTERISK = "*"
	SLASH    = "/"

	LT = "<"
	GT = ">"

	EQ     = "=="
	NOT_EQ = "!="

	// 分隔符
	COMMA     = ","
	SEMICOLON = ";"
	COLON     = ":"

	LPAREN   = "("
	RPAREN   = ")"
	LBRACE   = "{"
	RBRACE   = "}"
	LBRACKET = "["
	RBRACKET = "]"

	// 关键字
	FUNCTION = "FUNCTION"
	LET      = "LET"
	TRUE     = "TRUE"
	FALSE    = "FALSE"
	IF       = "IF"
	ELSE     = "ELSE"
	RETURN   = "RETURN"
)

1.3 词法分析器

定义

//lexer/lexer.go
package lexer

type Lexer struct {
	input string
	position int //当前字符位置
	readPosition int //下一个字符位置
	ch byte //当前字符
}

func New(input string) *Lexer {
	return &Lexer{input: input}
}

读取字符

//lexer/lexer.go
func (l *Lexer) readChar() {
	if l.readPosition >= len(l.input) { //到达input末尾
		l.ch = 0 //文件末尾
	} else {
		l.ch = l.input[l.readPosition]
	}
	l.position = l.readPosition
	l.readPosition += 1
}

func New(input string) *Lexer {
	l := &Lexer{input: input}
	l.readChar()
	return l
}

获取单字符词法单元

//lexer/lexer.go
package lexer

import "monkey/token"

func (l *Lexer) NextToken() token.Token {
	var tok token.Token
	switch l.ch {
	case '=':
		tok = newToken(token.ASSIGN, l.ch)
	case '+':
		tok = newToken(token.PLUS, l.ch)
	case '-':
		tok = newToken(token.MINUS, 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.COLON, 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 '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, l.ch)
	case 0:
		tok.Literal = ""
		tok.Type = token.EOF
	}

	l.readChar()
	return tok
}

func newToken(tokenType token.TokenType, ch byte) token.Token {
	return token.Token{Type: tokenType, Literal: string(ch)}
}

获取标识符词法单元

//lexer/lexer.go
package lexer

import "monkey/token"

func (l *Lexer) NextToken() token.Token {
	var tok token.Token
	switch l.ch {
	case '=':
		tok = newToken(token.ASSIGN, l.ch)
	case '+':
		tok = newToken(token.PLUS, l.ch)
	case '-':
		tok = newToken(token.MINUS, 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.COLON, 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 '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, l.ch)
	case 0:
		tok.Literal = ""
		tok.Type = token.EOF
	default:
		if isLetter(l.ch) {
			tok.Literal = l.readIdentifier()
			//判断关键字或者标识符
			tok.Type = token.LookupIdent(tok.Literal)
			return tok
		} else {
			tok = newToken(token.ILLEGAL, l.ch)
		}
	}

	l.readChar()
	return tok
}

//读取标识符字符串
func (l *Lexer) readIdentifier() string {
	position := l.position
	for isLetter(l.ch) {
		l.readChar()
	}
	return l.input[position:l.position]
}

//a-z_组成标识符
func isLetter(ch byte) bool {
	return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch == '_'
}

var keywords = map[string]TokenType{
	"fn":     FUNCTION,
	"let":    LET,
	"true":   TRUE,
	"false":  FALSE,
	"if":     IF,
	"else":   ELSE,
	"return": RETURN,
}

//判断标识符是是否是关键字
func LookupIdent(ident string) TokenType {
	if tok, ok := keywords[ident]; ok {
		return tok
	}
	return IDENT
}

跳过空白字符

//lexer/lexer.go
package lexer

import "monkey/token"

func (l *Lexer) NextToken() token.Token {
	var tok token.Token
	l.skipWhitespace()
	switch l.ch {
	case '=':
		tok = newToken(token.ASSIGN, l.ch)
	case '+':
		tok = newToken(token.PLUS, l.ch)
	case '-':
		tok = newToken(token.MINUS, 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.COLON, 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 '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, l.ch)
	case 0:
		tok.Literal = ""
		tok.Type = token.EOF
	default:
		if isLetter(l.ch) {
			tok.Literal = l.readIdentifier()
			//判断关键字或者标识符
			tok.Type = token.LookupIdent(tok.Literal)
			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()
	}
}

读取数字词法单元

//lexer/lexer.go
package lexer

import "monkey/token"

func (l *Lexer) NextToken() token.Token {
	var tok token.Token
	l.skipWhitespace()
	switch l.ch {
	case '=':
		tok = newToken(token.ASSIGN, l.ch)
	case '+':
		tok = newToken(token.PLUS, l.ch)
	case '-':
		tok = newToken(token.MINUS, 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.COLON, 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 '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, l.ch)
	case 0:
		tok.Literal = ""
		tok.Type = token.EOF
	default:
		if isLetter(l.ch) {
			tok.Literal = l.readIdentifier()
			//判断关键字或者标识符
			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
}

//读取数字
func (l *Lexer) readNumber() string {
	position := l.position
	for isDigit(l.ch) {
		l.readChar()
	}
	return l.input[position:l.position]
}

//0-9组成数字
func isDigit(ch byte) bool {
	return '0' <= ch && ch <= '9'
}

1.4 扩展词法单元和词法分析器

词法单元分类

单字符词法单元，-+/*等； 双字符词法单元，==等； 关键字词法单元，return等； 数字词法单元，12345等； 标识符词法单元，x等；

完整版词法单元解析

//lexer/lexer.go
package lexer

import "monkey/token"

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.COLON, 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 '"':
		tok.Type = token.STRING
		tok.Literal = l.readString()
	case '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, 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
}

//窥视下一个字符，不会移动当前字符位置
func (l *Lexer) peekChar() byte {
	if l.readPosition >= len(l.input) {
		return 0
	} else {
		return l.input[l.readPosition]
	}
}

1.5 编写REPL

Read-Eval-Print Loop（读取-求值-打印 循环），控制台或交互模式。

源代码转换为词法单元并打印

//repl/repl.go
package repl

import (
	"bufio"
	"fmt"
	"io"
	"monkey/lexer"
	"monkey/token"
)

const PROMPT = ">>"

func Start(in io.Reader, out io.Writer) {
	scanner := bufio.NewScanner(in)
	for {
		fmt.Fprintf(out, PROMPT)
		scanned := scanner.Scan()
		if !scanned { //Ctrl+C跳出循环
			return
		}

		line := scanner.Text()//按行读取代码
		l := lexer.New(line)

		for tok := l.NextToken(); tok.Type != token.EOF; tok = l.NextToken() {
			fmt.Fprintf(out, "%+v\n", tok)
		}
	}
}

//%v，打印结构体
 /*
type EqStruct struct{
	Name string
	Age  int32
}
e := EqStruct{Name:"2", Age:0}

//值
fmt.Printf("e=%v\n", e1)
//e={2 0}    

//字段名+值
fmt.Printf("e=%+v\n", e1)
//e={Name:2 Age:0}

//结构体值的Go语法表示
fmt.Printf("e=%#v\n", e1)
//e=main.EqStruct{Name:"2", Age:0} 
*/

主函数

//main.go
package main
import (
	"fmt"
	"monkey/repl"
	"os"
	"os/user"
)
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)
}

1.6 完整工程

monkey\token\token.go

package token

type TokenType string

const (
	ILLEGAL = "ILLEGAL"
	EOF     = "EOF"

	// 标识符+字面量
	IDENT = "IDENT" // add, foobar, x, y, ...
	INT   = "INT"   // 1343456

	// 运算符
	ASSIGN   = "="
	PLUS     = "+"
	MINUS    = "-"
	BANG     = "!"
	ASTERISK = "*"
	SLASH    = "/"

	LT = "<"
	GT = ">"

	EQ     = "=="
	NOT_EQ = "!="

	// 分隔符
	COMMA     = ","
	SEMICOLON = ";"

	LPAREN = "("
	RPAREN = ")"
	LBRACE = "{"
	RBRACE = "}"

	// 关键字
	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
}

monkey\lexer\lexer.go

package lexer

import "monkey/token"

type Lexer struct {
	input        string
	position     int  // 当前字符位置
	readPosition int  // 下一个字符位置
	ch           byte // 当前字符
}

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)}
}

monkey\lexer\lexer_test.go

package lexer

import (
	"testing"
	"monkey/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)
		}
	}
}

monkey\repl\repl.go

package repl

import (
	"bufio"
	"fmt"
	"io"
	"monkey/lexer"
	"monkey/token"
)

const PROMPT = ">>"

func Start(in io.Reader, out io.Writer) {
	scanner := bufio.NewScanner(in)

	for {
		fmt.Fprintf(out, 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.Fprintf(out, "%+v\n", tok)
		}
	}
}

monkey\main.go

package main

import (
	"fmt"
	"monkey/repl"
	"os"
	"os/user"
)

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)
}

monkey\run.txt

go mod init monkey

go test .\lexer

go run main.go
avatar
文章
阅读
粉丝