diff options
Diffstat (limited to 'lua/lexers/myrddin.lua')
| -rw-r--r-- | lua/lexers/myrddin.lua | 94 |
1 files changed, 37 insertions, 57 deletions
diff --git a/lua/lexers/myrddin.lua b/lua/lexers/myrddin.lua index a5b9b18..4b7f559 100644 --- a/lua/lexers/myrddin.lua +++ b/lua/lexers/myrddin.lua @@ -1,72 +1,52 @@ --- Copyright 2017 Michael Forney. See LICENSE +-- Copyright 2017-2022 Michael Forney. See LICENSE -- Myrddin LPeg lexer. -local l = require('lexer') -local token, word_match = l.token, l.word_match -local P, R, S, V = lpeg.P, lpeg.R, lpeg.S, lpeg.V +local lexer = require('lexer') +local token, word_match = lexer.token, lexer.word_match +local P, S = lpeg.P, lpeg.S -local M = {_NAME = 'myrddin'} +local lex = lexer.new('myrddin') -- Whitespace. -local ws = token(l.WHITESPACE, l.space^1) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1)) + +-- Keywords. +lex:add_rule('keyword', token(lexer.KEYWORD, word_match{ + 'break', 'const', 'continue', 'elif', 'else', 'extern', 'false', 'for', 'generic', 'goto', 'if', + 'impl', 'in', 'match', 'pkg', 'pkglocal', 'sizeof', 'struct', 'trait', 'true', 'type', 'union', + 'use', 'var', 'while' +})) + +-- Types. +lex:add_rule('type', token(lexer.TYPE, word_match{ + 'void', 'bool', 'char', 'byte', 'int', 'uint', 'int8', 'uint8', 'int16', 'uint16', 'int32', + 'uint32', 'int64', 'uint64', 'flt32', 'flt64' +} + '@' * lexer.word)) + +-- Identifiers. +lex:add_rule('identifier', token(lexer.IDENTIFIER, lexer.word)) -- Comments. -local line_comment = '//' * l.nonnewline_esc^0 -local block_comment = P{ - V'part' * P'*/'^-1, - part = '/*' * (V'full' + (l.any - '/*' - '*/'))^0, - full = V'part' * '*/', -} -local comment = token(l.COMMENT, line_comment + block_comment) +local line_comment = lexer.to_eol('//', true) +local block_comment = lexer.range('/*', '*/', false, false, true) +lex:add_rule('comment', token(lexer.COMMENT, line_comment + block_comment)) -- Strings. -local sq_str = l.delimited_range("'", true) -local dq_str = l.delimited_range('"', true) -local string = token(l.STRING, sq_str + dq_str) +local sq_str = lexer.range("'", true) +local dq_str = lexer.range('"', true) +lex:add_rule('string', token(lexer.STRING, sq_str + dq_str)) -- Numbers. -local digit = l.digit + '_' -local bdigit = R'01' + '_' -local xdigit = l.xdigit + '_' -local odigit = R'07' + '_' +local digit = lexer.digit + '_' +local bdigit = S('01') + '_' +local xdigit = lexer.xdigit + '_' +local odigit = lpeg.R('07') + '_' local integer = '0x' * xdigit^1 + '0o' * odigit^1 + '0b' * bdigit^1 + digit^1 -local float = digit^1 * (('.' * digit^1) * (S'eE' * S'+-'^-1 * digit^1)^-1 + - ('.' * digit^1)^-1 * S'eE' * S'+-'^-1 * digit^1) -local number = token(l.NUMBER, float + integer) - --- Keywords. -local keyword = token(l.KEYWORD, word_match{ - 'break', 'const', 'continue', 'elif', 'else', 'extern', 'false', 'for', - 'generic', 'goto', 'if', 'impl', 'in', 'match', 'pkg', 'pkglocal', 'sizeof', - 'struct', 'trait', 'true', 'type', 'union', 'use', 'var', 'while', -}) - --- Types. -local type = token(l.TYPE, word_match{ - 'void', 'bool', 'char', 'byte', - 'int8', 'uint8', - 'int16', 'uint16', - 'int32', 'uint32', - 'int64', 'uint64', - 'int', 'uint', - 'flt32', 'flt64', -} + '@' * l.word) - --- Identifiers. -local identifier = token(l.IDENTIFIER, l.word) +local float = digit^1 * ((('.' * digit^1) * (S('eE') * S('+-')^-1 * digit^1)^-1) + + (('.' * digit^1)^-1 * S('eE') * S('+-')^-1 * digit^1)) +lex:add_rule('number', token(lexer.NUMBER, float + integer)) -- Operators. -local operator = token(l.OPERATOR, S'`#_+-/*%<>~!=^&|~:;,.()[]{}') - -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'type', type}, - {'identifier', identifier}, - {'string', string}, - {'comment', comment}, - {'number', number}, - {'operator', operator}, -} +lex:add_rule('operator', token(lexer.OPERATOR, S('`#_+-/*%<>~!=^&|~:;,.()[]{}'))) -return M +return lex |
