parse arithmetic binary expressions

This commit is contained in:
2026-08-10 23:35:10 +02:00
parent 891dc6516e
commit 8dd06afde2
10 changed files with 358 additions and 120 deletions
+79 -50
View File
@@ -3,7 +3,6 @@ import "@std/mem"
import "@std/strmap"
import "@std/enums/enummap"
import "@std/arraylist"
import "@std/debug"
import "@source/strpool"
@@ -43,8 +42,6 @@ keywords std.StringMap(TokenKind) :: strmap.init([
{ "while", .while },
])
TokenId :: distinct u32
Diagnostic :: struct {
token TokenId
code ErrorCode
@@ -68,7 +65,6 @@ deinit proc(state @mut State) void {
}
scan proc(state @mut State, program []u8) void ! (mem.AllocError | strpool.InternError) {
tokens :: &state.tokens
diagnostics :: &state.diagnostics
cursor := 0
@@ -77,7 +73,7 @@ scan proc(state @mut State, program []u8) void ! (mem.AllocError | strpool.Inter
# whitespace
if char == '\n' {
try add_token(tokens, Token{ kind = .newline, start = cursor })
try add_token(state, Token{ start = cursor, kind = .newline })
cursor += 1
continue
} else if is_whitespace(char) {
@@ -96,9 +92,9 @@ scan proc(state @mut State, program []u8) void ! (mem.AllocError | strpool.Inter
if is_alpha(char) or char == '_' {
start :: cursor
result :: scan_ident(start, program)
try add_token(tokens, Token{
kind = result.kind,
try add_token(state, Token{
start = start,
kind = result.kind,
str_id = result.str_id,
})
cursor = result.end
@@ -109,15 +105,15 @@ scan proc(state @mut State, program []u8) void ! (mem.AllocError | strpool.Inter
if is_digit(char) {
start :: cursor
result :: scan_number(start, program) catch |err| {
token :: token_id(tokens.items.len)
try add_token(tokens, Token{ kind = .invalid, start = start })
token :: token_id(state.tokens.items.len)
try add_token(state, Token{ start = start, kind = .invalid })
try arraylist.append(diagnostics, Diagnostic{ token = token, code = err.code })
cursor = err.end
continue
}
kind :: if (result.has_decimal) .float else .int
try add_token(tokens, Token{ kind = kind, start = start })
try add_token(state, Token{ start = start, kind = kind })
cursor = result.end
continue
}
@@ -126,68 +122,107 @@ scan proc(state @mut State, program []u8) void ! (mem.AllocError | strpool.Inter
if char == '"' {
start :: cursor
result :: scan_string(start, program) catch |err| {
token :: token_id(tokens.items.len)
try add_token(tokens, Token{ kind = .invalid, start = start })
token :: token_id(state.tokens.items.len)
try add_token(state, Token{ start = start, kind = .invalid })
try arraylist.append(diagnostics, Diagnostic{ token = token, code = err.code })
cursor = err.end
continue
}
try add_token(tokens, Token{ kind = .string, start = start })
try add_token(state, Token{ start = start, kind = .string })
cursor = result.end
continue
}
# immutable assignment or single colon
# immutable decl, mutable decl, or single colon
if char == ':' {
if cursor + 1 < program.len and program[cursor + 1] == ':' {
try add_token(tokens, Token{ kind = .double_colon, start = cursor })
try add_token(state, Token{ start = cursor, kind = .double_colon })
cursor += 2
continue
}
try add_token(tokens, Token{ kind = .colon, start = cursor })
if cursor + 1 < program.len and program[cursor + 1] == '=' {
try add_token(state, Token{ start = cursor, kind = .colon_equal })
cursor += 2
continue
}
try add_token(state, Token{ start = cursor, kind = .colon })
cursor += 1
continue
}
# mutable reassignment
if char == '=' {
try add_token(tokens, Token{ kind = .equal, start = cursor })
# compound arithmetic assignment
if char == '+' {
if cursor + 1 < program.len and program[cursor + 1] == '=' {
try add_token(state, Token{ start = cursor, kind = .plus_equal })
cursor += 2
continue
}
try add_token(state, Token{ start = cursor, kind = .plus })
cursor += 1
continue
}
if char == '-' {
if cursor + 1 < program.len and program[cursor + 1] == '=' {
try add_token(state, Token{ start = cursor, kind = .minus_equal })
cursor += 2
continue
}
try add_token(state, Token{ start = cursor, kind = .minus })
cursor += 1
continue
}
if char == '*' {
if cursor + 1 < program.len and program[cursor + 1] == '=' {
try add_token(state, Token{ start = cursor, kind = .star_equal })
cursor += 2
continue
}
try add_token(state, Token{ start = cursor, kind = .star })
cursor += 1
continue
}
if char == '/' {
if cursor + 1 < program.len and program[cursor + 1] == '=' {
try add_token(state, Token{ start = cursor, kind = .slash_equal })
cursor += 2
continue
}
try add_token(state, Token{ start = cursor, kind = .slash })
cursor += 1
continue
}
# parentheses
if char == '(' {
try add_token(tokens, Token{ kind = .open_paren, start = cursor })
cursor += 1
continue
} else if char == ')' {
try add_token(tokens, Token{ kind = .close_paren, start = cursor })
cursor += 1
continue
# single character tokens
kind ?TokenKind :: match char {
'=': .equal
'(': .open_paren
')': .close_paren
'{': .open_curly
'}': .close_curly
else: null
}
# curly braces
if char == '{' {
try add_token(tokens, Token{ kind = .open_curly, start = cursor })
cursor += 1
continue
} else if char == '}' {
try add_token(tokens, Token{ kind = .close_curly, start = cursor })
if (kind) |k| {
try add_token(state, Token{ start = cursor, kind = k })
cursor += 1
continue
}
# invalid character
token :: token_id(tokens.items.len)
token :: token_id(state.tokens.items.len)
try add_token(state, Token{ start = cursor, kind = .invalid })
try arraylist.append(diagnostics, Diagnostic{ token = token, code = .invalid_character })
try add_token(tokens, Token{ kind = .invalid, start = cursor })
cursor += 1
}
try add_token(tokens, Token{ kind = .eof, start = cursor })
try add_token(state, Token{ start = cursor, kind = .eof })
}
ScanIdentResult :: struct {
@@ -210,9 +245,9 @@ scan_ident proc(start usize, program []u8) ScanIdentResult {
# don't intern keywords (already O(1) lookup via token kind)
str_id :: if (kind == .ident)
strpool.intern(&strpool.strings, program[start..cursor]) catch strpool.NO_ID
strpool.intern(&strpool.strings, program[start..cursor]) catch strpool.NO_ID_STR
else
strpool.NO_ID
strpool.NO_ID_STR
return ScanIdentResult{
end = cursor,
@@ -243,7 +278,7 @@ scan_number proc(start usize, program []u8) ScanNumResult ! ScanError {
if has_decimal and (cursor >= program.len or !is_digit(program[cursor])) {
return ScanError{
code = .float_must_end_with_digit,
end = cursor + 1,
end = cursor,
}
}
@@ -300,13 +335,7 @@ is_digit proc(char u8) bool {
}
@hide
add_token proc(tokens @mut std.ArrayList(Token), token Token) void ! mem.AllocError {
_ = token_id(tokens.items.len)
try arraylist.append(tokens, token)
}
@hide
token_id proc(idx uint) TokenId {
debug.assert(u64(idx) < u64(maxval!(TokenId)))
return TokenId(idx)
add_token proc(state @mut State, token Token) void ! mem.AllocError {
_ = token_id(state.tokens.items.len)
try arraylist.append(&state.tokens, token)
}