Muki/scanner.cpp at master · Chand-ra/Muki · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
#include "scanner.h"

static std::unordered_map<std::string, Token::Type> keywords = {
			{"and", Token::AND}, {"class", Token::CLASS}, {"or", Token::OR}, {"else", Token::ELSE},
			{"false", Token::FALSE}, {"for", Token::FOR}, {"fun", Token::FUN}, {"if", Token::IF},
			{"null", Token::NUL}, {"print", Token::PRINT}, {"return", Token::RETURN}, {"super", Token::SUPER},
			{"this", Token::THIS}, {"true", Token::TRUE}, {"let", Token::LET}, {"while", Token::WHILE} };

bool Scanner::isDigit(char c) {
	return (c >= '0' && c <= '9');
}

bool Scanner::isAlpha(char c) {
	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c == '_');
}

void Scanner::error(std::string message) {
	hadError = true;
	std::cerr << "error: " << message << std::endl;
}

std::vector<Token> Scanner::getTokens(std::istream& input, bool& err) {
	auto match{
		[&](char c) {
			char a = input.get();
			if (a != EOF && c == a)
				return true;
			else
				input.unget();
			return false;
		}
	};
	std::vector<Token> tokens;
	for (char c = input.get(); c != EOF; c = input.get()) {
		switch (c) {
		case ' ':
		case '\r':
		case '\t':
			break;
		case '\n':
			lineNum++;
			break;
		case '(':
			tokens.push_back(Token::LPARAN); break;
		case ')':
			tokens.push_back(Token::RPARAN); break;
		case '{':
			tokens.push_back(Token::LBRACE); break;
		case '}':
			tokens.push_back(Token::RBRACE); break;
		case '.':
			tokens.push_back(Token::DOT); break;
		case ',':
			tokens.push_back(Token::COMMA); break;
		case '+':
			tokens.push_back(Token::PLUS); break;
		case '-':
			tokens.push_back(Token::MINUS); break;
		case '*':
			tokens.push_back(Token::STAR); break;
		case ';':
			tokens.push_back(Token::SEMICOLON); break;
		case '/':
			if (match('/')) {
				while ((c = input.get()) && c != EOF && c != '\n');
				lineNum++;
			}
			else
				tokens.push_back(Token::SLASH);
			break;
		case '!':
			tokens.push_back(match('=') ? Token::UNEQUAL : Token::BANG); break;
		case '=':
			tokens.push_back(match('=') ? Token::EQUAL : Token::ASSIGN); break;
		case '>':
			tokens.push_back(match('=') ? Token::GREATEREQ : Token::GREATER); break;
		case '<':
			tokens.push_back(match('=') ? Token::LESSEREQ : Token::LESSER); break;
		case '"':
		{
			std::string stringLit{ "" };
			while ((c = input.get()) && c != EOF && c != '"') {
				if (c == '\n')
					lineNum++;
				stringLit += c;
			}
			if (c == EOF)
				error("Unterminated string");
			tokens.push_back(Token(Token::STRING, stringLit));
			break;
		}
		default:
			if (isDigit(c)) {
				std::string num{ c };
				while (isDigit(c = input.get()))
					num += c;
				if (c == '.') {
					num += c;
					while (isDigit(c = input.get()))
						num += c;
				}
				tokens.push_back(Token(Token::NUM, num));
				input.unget();
			}
			else if (isAlpha(c)) {
				std::string s{ c };
				while ((c = input.get()) && (isAlpha(c) || isDigit(c)))
					s += c;
				tokens.push_back(keywords.find(s) != keywords.end() ? keywords[s] : Token(Token::IDENTIFIER, s));
				input.unget();
			}
			else
				error("Unknown token at line " + std::to_string(lineNum));
		}
	}
	tokens.push_back(Token::FILEEND);
	err = hadError;
	return std::move(tokens);
}