510 lines
16 KiB
Zig
510 lines
16 KiB
Zig
const std = @import("std");
|
|
const mem = std.mem;
|
|
|
|
pub const Token = struct {
|
|
id: Id,
|
|
start: usize,
|
|
end: usize,
|
|
|
|
const KeywordId = struct {
|
|
bytes: []const u8,
|
|
id: Id,
|
|
};
|
|
|
|
const keywords = []KeywordId {
|
|
KeywordId{.bytes="align", .id = Id.Keyword_align},
|
|
KeywordId{.bytes="and", .id = Id.Keyword_and},
|
|
KeywordId{.bytes="asm", .id = Id.Keyword_asm},
|
|
KeywordId{.bytes="break", .id = Id.Keyword_break},
|
|
KeywordId{.bytes="coldcc", .id = Id.Keyword_coldcc},
|
|
KeywordId{.bytes="comptime", .id = Id.Keyword_comptime},
|
|
KeywordId{.bytes="const", .id = Id.Keyword_const},
|
|
KeywordId{.bytes="continue", .id = Id.Keyword_continue},
|
|
KeywordId{.bytes="defer", .id = Id.Keyword_defer},
|
|
KeywordId{.bytes="else", .id = Id.Keyword_else},
|
|
KeywordId{.bytes="enum", .id = Id.Keyword_enum},
|
|
KeywordId{.bytes="error", .id = Id.Keyword_error},
|
|
KeywordId{.bytes="export", .id = Id.Keyword_export},
|
|
KeywordId{.bytes="extern", .id = Id.Keyword_extern},
|
|
KeywordId{.bytes="false", .id = Id.Keyword_false},
|
|
KeywordId{.bytes="fn", .id = Id.Keyword_fn},
|
|
KeywordId{.bytes="for", .id = Id.Keyword_for},
|
|
KeywordId{.bytes="goto", .id = Id.Keyword_goto},
|
|
KeywordId{.bytes="if", .id = Id.Keyword_if},
|
|
KeywordId{.bytes="inline", .id = Id.Keyword_inline},
|
|
KeywordId{.bytes="nakedcc", .id = Id.Keyword_nakedcc},
|
|
KeywordId{.bytes="noalias", .id = Id.Keyword_noalias},
|
|
KeywordId{.bytes="null", .id = Id.Keyword_null},
|
|
KeywordId{.bytes="or", .id = Id.Keyword_or},
|
|
KeywordId{.bytes="packed", .id = Id.Keyword_packed},
|
|
KeywordId{.bytes="pub", .id = Id.Keyword_pub},
|
|
KeywordId{.bytes="return", .id = Id.Keyword_return},
|
|
KeywordId{.bytes="stdcallcc", .id = Id.Keyword_stdcallcc},
|
|
KeywordId{.bytes="struct", .id = Id.Keyword_struct},
|
|
KeywordId{.bytes="switch", .id = Id.Keyword_switch},
|
|
KeywordId{.bytes="test", .id = Id.Keyword_test},
|
|
KeywordId{.bytes="this", .id = Id.Keyword_this},
|
|
KeywordId{.bytes="true", .id = Id.Keyword_true},
|
|
KeywordId{.bytes="undefined", .id = Id.Keyword_undefined},
|
|
KeywordId{.bytes="union", .id = Id.Keyword_union},
|
|
KeywordId{.bytes="unreachable", .id = Id.Keyword_unreachable},
|
|
KeywordId{.bytes="use", .id = Id.Keyword_use},
|
|
KeywordId{.bytes="var", .id = Id.Keyword_var},
|
|
KeywordId{.bytes="volatile", .id = Id.Keyword_volatile},
|
|
KeywordId{.bytes="while", .id = Id.Keyword_while},
|
|
};
|
|
|
|
fn getKeyword(bytes: []const u8) -> ?Id {
|
|
for (keywords) |kw| {
|
|
if (mem.eql(u8, kw.bytes, bytes)) {
|
|
return kw.id;
|
|
}
|
|
}
|
|
return null;
|
|
}
|
|
|
|
const StrLitKind = enum {Normal, C};
|
|
|
|
pub const Id = union(enum) {
|
|
Invalid,
|
|
Identifier,
|
|
StringLiteral: StrLitKind,
|
|
Eof,
|
|
Builtin,
|
|
Bang,
|
|
Equal,
|
|
EqualEqual,
|
|
BangEqual,
|
|
LParen,
|
|
RParen,
|
|
Semicolon,
|
|
Percent,
|
|
LBrace,
|
|
RBrace,
|
|
Period,
|
|
Ellipsis2,
|
|
Ellipsis3,
|
|
Minus,
|
|
Arrow,
|
|
Colon,
|
|
Slash,
|
|
Comma,
|
|
Ampersand,
|
|
AmpersandEqual,
|
|
IntegerLiteral,
|
|
FloatLiteral,
|
|
Keyword_align,
|
|
Keyword_and,
|
|
Keyword_asm,
|
|
Keyword_break,
|
|
Keyword_coldcc,
|
|
Keyword_comptime,
|
|
Keyword_const,
|
|
Keyword_continue,
|
|
Keyword_defer,
|
|
Keyword_else,
|
|
Keyword_enum,
|
|
Keyword_error,
|
|
Keyword_export,
|
|
Keyword_extern,
|
|
Keyword_false,
|
|
Keyword_fn,
|
|
Keyword_for,
|
|
Keyword_goto,
|
|
Keyword_if,
|
|
Keyword_inline,
|
|
Keyword_nakedcc,
|
|
Keyword_noalias,
|
|
Keyword_null,
|
|
Keyword_or,
|
|
Keyword_packed,
|
|
Keyword_pub,
|
|
Keyword_return,
|
|
Keyword_stdcallcc,
|
|
Keyword_struct,
|
|
Keyword_switch,
|
|
Keyword_test,
|
|
Keyword_this,
|
|
Keyword_true,
|
|
Keyword_undefined,
|
|
Keyword_union,
|
|
Keyword_unreachable,
|
|
Keyword_use,
|
|
Keyword_var,
|
|
Keyword_volatile,
|
|
Keyword_while,
|
|
};
|
|
};
|
|
|
|
pub const Tokenizer = struct {
|
|
buffer: []const u8,
|
|
index: usize,
|
|
|
|
pub const Location = struct {
|
|
line: usize,
|
|
column: usize,
|
|
line_start: usize,
|
|
line_end: usize,
|
|
};
|
|
|
|
pub fn getTokenLocation(self: &Tokenizer, token: &const Token) -> Location {
|
|
var loc = Location {
|
|
.line = 0,
|
|
.column = 0,
|
|
.line_start = 0,
|
|
.line_end = 0,
|
|
};
|
|
for (self.buffer) |c, i| {
|
|
if (i == token.start) {
|
|
loc.line_end = i;
|
|
while (loc.line_end < self.buffer.len and self.buffer[loc.line_end] != '\n') : (loc.line_end += 1) {}
|
|
return loc;
|
|
}
|
|
if (c == '\n') {
|
|
loc.line += 1;
|
|
loc.column = 0;
|
|
loc.line_start = i + 1;
|
|
} else {
|
|
loc.column += 1;
|
|
}
|
|
}
|
|
return loc;
|
|
}
|
|
|
|
/// For debugging purposes
|
|
pub fn dump(self: &Tokenizer, token: &const Token) {
|
|
std.debug.warn("{} \"{}\"\n", @tagName(token.id), self.buffer[token.start..token.end]);
|
|
}
|
|
|
|
pub fn init(buffer: []const u8) -> Tokenizer {
|
|
return Tokenizer {
|
|
.buffer = buffer,
|
|
.index = 0,
|
|
};
|
|
}
|
|
|
|
const State = enum {
|
|
Start,
|
|
Identifier,
|
|
Builtin,
|
|
C,
|
|
StringLiteral,
|
|
StringLiteralBackslash,
|
|
Equal,
|
|
Bang,
|
|
Minus,
|
|
Slash,
|
|
LineComment,
|
|
Zero,
|
|
IntegerLiteral,
|
|
NumberDot,
|
|
FloatFraction,
|
|
FloatExponentUnsigned,
|
|
FloatExponentNumber,
|
|
Ampersand,
|
|
Period,
|
|
Period2,
|
|
};
|
|
|
|
pub fn next(self: &Tokenizer) -> Token {
|
|
var state = State.Start;
|
|
var result = Token {
|
|
.id = Token.Id.Eof,
|
|
.start = self.index,
|
|
.end = undefined,
|
|
};
|
|
while (self.index < self.buffer.len) : (self.index += 1) {
|
|
const c = self.buffer[self.index];
|
|
switch (state) {
|
|
State.Start => switch (c) {
|
|
' ', '\n' => {
|
|
result.start = self.index + 1;
|
|
},
|
|
'c' => {
|
|
state = State.C;
|
|
result.id = Token.Id.Identifier;
|
|
},
|
|
'"' => {
|
|
state = State.StringLiteral;
|
|
result.id = Token.Id { .StringLiteral = Token.StrLitKind.Normal };
|
|
},
|
|
'a'...'b', 'd'...'z', 'A'...'Z', '_' => {
|
|
state = State.Identifier;
|
|
result.id = Token.Id.Identifier;
|
|
},
|
|
'@' => {
|
|
state = State.Builtin;
|
|
result.id = Token.Id.Builtin;
|
|
},
|
|
'=' => {
|
|
state = State.Equal;
|
|
},
|
|
'!' => {
|
|
state = State.Bang;
|
|
},
|
|
'(' => {
|
|
result.id = Token.Id.LParen;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
')' => {
|
|
result.id = Token.Id.RParen;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
';' => {
|
|
result.id = Token.Id.Semicolon;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
',' => {
|
|
result.id = Token.Id.Comma;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
':' => {
|
|
result.id = Token.Id.Colon;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
'%' => {
|
|
result.id = Token.Id.Percent;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
'{' => {
|
|
result.id = Token.Id.LBrace;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
'}' => {
|
|
result.id = Token.Id.RBrace;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
'.' => {
|
|
state = State.Period;
|
|
},
|
|
'-' => {
|
|
state = State.Minus;
|
|
},
|
|
'/' => {
|
|
state = State.Slash;
|
|
},
|
|
'&' => {
|
|
state = State.Ampersand;
|
|
},
|
|
'0' => {
|
|
state = State.Zero;
|
|
result.id = Token.Id.IntegerLiteral;
|
|
},
|
|
'1'...'9' => {
|
|
state = State.IntegerLiteral;
|
|
result.id = Token.Id.IntegerLiteral;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Invalid;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
},
|
|
State.Ampersand => switch (c) {
|
|
'=' => {
|
|
result.id = Token.Id.AmpersandEqual;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Ampersand;
|
|
break;
|
|
},
|
|
},
|
|
State.Identifier => switch (c) {
|
|
'a'...'z', 'A'...'Z', '_', '0'...'9' => {},
|
|
else => {
|
|
if (Token.getKeyword(self.buffer[result.start..self.index])) |id| {
|
|
result.id = id;
|
|
}
|
|
break;
|
|
},
|
|
},
|
|
State.Builtin => switch (c) {
|
|
'a'...'z', 'A'...'Z', '_', '0'...'9' => {},
|
|
else => break,
|
|
},
|
|
State.C => switch (c) {
|
|
'\\' => @panic("TODO"),
|
|
'"' => {
|
|
state = State.StringLiteral;
|
|
result.id = Token.Id { .StringLiteral = Token.StrLitKind.C };
|
|
},
|
|
'a'...'z', 'A'...'Z', '_', '0'...'9' => {
|
|
state = State.Identifier;
|
|
},
|
|
else => break,
|
|
},
|
|
State.StringLiteral => switch (c) {
|
|
'\\' => {
|
|
state = State.StringLiteralBackslash;
|
|
},
|
|
'"' => {
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
'\n' => break, // Look for this error later.
|
|
else => {},
|
|
},
|
|
|
|
State.StringLiteralBackslash => switch (c) {
|
|
'\n' => break, // Look for this error later.
|
|
else => {
|
|
state = State.StringLiteral;
|
|
},
|
|
},
|
|
|
|
State.Bang => switch (c) {
|
|
'=' => {
|
|
result.id = Token.Id.BangEqual;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Bang;
|
|
break;
|
|
},
|
|
},
|
|
|
|
State.Equal => switch (c) {
|
|
'=' => {
|
|
result.id = Token.Id.EqualEqual;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Equal;
|
|
break;
|
|
},
|
|
},
|
|
|
|
State.Minus => switch (c) {
|
|
'>' => {
|
|
result.id = Token.Id.Arrow;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Minus;
|
|
break;
|
|
},
|
|
},
|
|
|
|
State.Period => switch (c) {
|
|
'.' => {
|
|
state = State.Period2;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Period;
|
|
break;
|
|
},
|
|
},
|
|
|
|
State.Period2 => switch (c) {
|
|
'.' => {
|
|
result.id = Token.Id.Ellipsis3;
|
|
self.index += 1;
|
|
break;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Ellipsis2;
|
|
break;
|
|
},
|
|
},
|
|
|
|
State.Slash => switch (c) {
|
|
'/' => {
|
|
result.id = undefined;
|
|
state = State.LineComment;
|
|
},
|
|
else => {
|
|
result.id = Token.Id.Slash;
|
|
break;
|
|
},
|
|
},
|
|
State.LineComment => switch (c) {
|
|
'\n' => {
|
|
state = State.Start;
|
|
result = Token {
|
|
.id = Token.Id.Eof,
|
|
.start = self.index + 1,
|
|
.end = undefined,
|
|
};
|
|
},
|
|
else => {},
|
|
},
|
|
State.Zero => switch (c) {
|
|
'b', 'o', 'x' => {
|
|
state = State.IntegerLiteral;
|
|
},
|
|
else => {
|
|
// reinterpret as a normal number
|
|
self.index -= 1;
|
|
state = State.IntegerLiteral;
|
|
},
|
|
},
|
|
State.IntegerLiteral => switch (c) {
|
|
'.' => {
|
|
state = State.NumberDot;
|
|
},
|
|
'p', 'P', 'e', 'E' => {
|
|
state = State.FloatExponentUnsigned;
|
|
},
|
|
'0'...'9', 'a'...'f', 'A'...'F' => {},
|
|
else => break,
|
|
},
|
|
State.NumberDot => switch (c) {
|
|
'.' => {
|
|
self.index -= 1;
|
|
state = State.Start;
|
|
break;
|
|
},
|
|
else => {
|
|
self.index -= 1;
|
|
result.id = Token.Id.FloatLiteral;
|
|
state = State.FloatFraction;
|
|
},
|
|
},
|
|
State.FloatFraction => switch (c) {
|
|
'p', 'P', 'e', 'E' => {
|
|
state = State.FloatExponentUnsigned;
|
|
},
|
|
'0'...'9', 'a'...'f', 'A'...'F' => {},
|
|
else => break,
|
|
},
|
|
State.FloatExponentUnsigned => switch (c) {
|
|
'+', '-' => {
|
|
state = State.FloatExponentNumber;
|
|
},
|
|
else => {
|
|
// reinterpret as a normal exponent number
|
|
self.index -= 1;
|
|
state = State.FloatExponentNumber;
|
|
}
|
|
},
|
|
State.FloatExponentNumber => switch (c) {
|
|
'0'...'9', 'a'...'f', 'A'...'F' => {},
|
|
else => break,
|
|
},
|
|
}
|
|
}
|
|
result.end = self.index;
|
|
// TODO check state when returning EOF
|
|
return result;
|
|
}
|
|
|
|
pub fn getTokenSlice(self: &const Tokenizer, token: &const Token) -> []const u8 {
|
|
return self.buffer[token.start..token.end];
|
|
}
|
|
};
|
|
|
|
|