commit e0dd19e78c6fae540f403c99216fd4a89ab6f20b
parent 1db4b03a50474862ea143ad3bbe586f3feb03dd9
Author: citbl <citbl@citbl.org>
Date: Sat, 23 May 2026 23:51:11 +1000
refac
Diffstat:
| M | mtcl/lexer.lua | | | 149 | ++++++++++++++++++++++++------------------------------------------------------- |
1 file changed, 44 insertions(+), 105 deletions(-)
diff --git a/mtcl/lexer.lua b/mtcl/lexer.lua
@@ -1,4 +1,9 @@
-local lexer = { tokens = {} }
+local lexer = {
+ tokens = {},
+ file = "",
+ line = 1,
+ pos = 1,
+}
local a = string.byte("a")
local z = string.byte("z")
@@ -93,10 +98,19 @@ local function print_token(t)
)
end
+function lexer:add(kind, lexeme)
+ token = {
+ kind = kind,
+ lexeme = lexeme,
+ file = self.file,
+ line = self.line,
+ col = self.col,
+ }
+ table.insert(self.tokens, token)
+end
+
function lexer:lex(file, src)
local i = 1
- local line, col = 1, 1
- local tokens = {}
local function next()
if i + 1 <= #src then
@@ -110,142 +124,67 @@ function lexer:lex(file, src)
if is_space(c) then
-- skip...
if c == "\n" then
- col = 1
- line = line + 1
+ self.col = 1
+ self.line = self.line + 1
else
- col = col + 1
+ self.col = self.col + 1
end
elseif is_alpha(c:byte()) then
word, i = read_ident(i, src)
- col = i
- tokens[#tokens + 1] = {
- kind = TK.IDENT,
- lexeme = word,
- file = file,
- line = line,
- col = col,
- }
+ self.col = i
+ self:add(TK.IDENT, word)
elseif is_digit(c:byte()) then
number, i, is_float = read_number(i, src)
- col = i
- local kind = TK.IDK
+ self.col = i
if is_float then
- kind = TK.LIT_FLOAT
+ self:add(TK.LIT_FLOAT, number)
else
- kind = TK.LIT_INT
+ self:add(TK.LIT_INT, number)
end
- tokens[#tokens + 1] = {
- kind = kind,
- lexeme = number,
- file = file,
- line = line,
- col = col,
- }
elseif c == ":" then
if next() == ":" then
- tokens[#tokens + 1] = {
- kind = TK.COLONCOLON,
- lexeme = "::",
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.COLONCOLON, "::")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
else
- tokens[#tokens + 1] = {
- kind = TK.COLON,
- lexeme = ":",
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.COLON, ":")
end
elseif c == "=" then
if next() == "=" then
- tokens[#tokens + 1] = {
- kind = TK.EQEQ,
- lexeme = "==",
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.EQEQ, "==")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
else
- tokens[#tokens + 1] = {
- kind = TK.EQ,
- lexeme = "=",
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.EQ, "=")
end
elseif c == "(" then
- tokens[#tokens + 1] = {
- kind = TK.L_PAREN,
- lexeme = "(",
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.L_PAREN, "(")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
elseif c == ")" then
- tokens[#tokens + 1] = {
- kind = TK.R_PAREN,
- lexeme = ")",
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.R_PAREN, ")")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
elseif c == "'" then
- tokens[#tokens + 1] = {
- kind = TK.SGL_QUOTE,
- lexeme = "'",
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.SGL_QUOTE, "'")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
elseif c == '"' then
- tokens[#tokens + 1] = {
- kind = TK.DBL_QUOTE,
- lexeme = '"',
-
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.DBL_QUOTE, '"')
i = i + 1
- col = col + 1
+ self.col = self.col + 1
else
- tokens[#tokens + 1] = {
- kind = TK.IDK,
- lexeme = "",
- file = file,
- line = line,
- col = col,
- }
+ self:add(TK.IDK, "")
i = i + 1
- col = col + 1
+ self.col = self.col + 1
end
i = i + 1
- col = col + 1
+ self.col = self.col + 1
end
- for i = 1, #tokens do
- print_token(tokens[i])
+ for i = 1, #self.tokens do
+ print_token(self.tokens[i])
end
- self.tokens = tokens
end
return lexer
