diff options
Diffstat (limited to 'lua/lexers/boo.lua')
| -rw-r--r-- | lua/lexers/boo.lua | 103 |
1 files changed, 43 insertions, 60 deletions
diff --git a/lua/lexers/boo.lua b/lua/lexers/boo.lua index 01d989e..5b6a6e4 100644 --- a/lua/lexers/boo.lua +++ b/lua/lexers/boo.lua @@ -1,81 +1,64 @@ --- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE. +-- Copyright 2006-2022 Mitchell. See LICENSE. -- Boo LPeg lexer. -local l = require('lexer') -local token, word_match = l.token, l.word_match -local P, R, S = lpeg.P, lpeg.R, lpeg.S +local lexer = require('lexer') +local token, word_match = lexer.token, lexer.word_match +local P, S = lpeg.P, lpeg.S -local M = {_NAME = 'boo'} +local lex = lexer.new('boo') -- Whitespace. -local ws = token(l.WHITESPACE, l.space^1) - --- Comments. -local line_comment = '#' * l.nonnewline_esc^0 -local block_comment = '/*' * (l.any - '*/')^0 * P('*/')^-1 -local comment = token(l.COMMENT, line_comment + block_comment) - --- Strings. -local sq_str = l.delimited_range("'", true) -local dq_str = l.delimited_range('"', true) -local triple_dq_str = '"""' * (l.any - '"""')^0 * P('"""')^-1 -local regex_str = #('/') * l.last_char_includes('!%^&*([{-=+|:;,?<>~') * - l.delimited_range('/', true) -local string = token(l.STRING, triple_dq_str + sq_str + dq_str) + - token(l.REGEX, regex_str) - - --- Numbers. -local number = token(l.NUMBER, (l.float + l.integer) * - (S('msdhsfFlL') + 'ms')^-1) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1)) -- Keywords. -local keyword = token(l.KEYWORD, word_match{ - 'and', 'break', 'cast', 'continue', 'elif', 'else', 'ensure', 'except', 'for', - 'given', 'goto', 'if', 'in', 'isa', 'is', 'not', 'or', 'otherwise', 'pass', - 'raise', 'ref', 'try', 'unless', 'when', 'while', +lex:add_rule('keyword', token(lexer.KEYWORD, word_match{ + 'and', 'break', 'cast', 'continue', 'elif', 'else', 'ensure', 'except', 'for', 'given', 'goto', + 'if', 'in', 'isa', 'is', 'not', 'or', 'otherwise', 'pass', 'raise', 'ref', 'try', 'unless', + 'when', 'while', -- Definitions. - 'abstract', 'callable', 'class', 'constructor', 'def', 'destructor', 'do', - 'enum', 'event', 'final', 'get', 'interface', 'internal', 'of', 'override', - 'partial', 'private', 'protected', 'public', 'return', 'set', 'static', - 'struct', 'transient', 'virtual', 'yield', + 'abstract', 'callable', 'class', 'constructor', 'def', 'destructor', 'do', 'enum', 'event', + 'final', 'get', 'interface', 'internal', 'of', 'override', 'partial', 'private', 'protected', + 'public', 'return', 'set', 'static', 'struct', 'transient', 'virtual', 'yield', -- Namespaces. 'as', 'from', 'import', 'namespace', -- Other. 'self', 'super', 'null', 'true', 'false' -}) +})) -- Types. -local type = token(l.TYPE, word_match{ - 'bool', 'byte', 'char', 'date', 'decimal', 'double', 'duck', 'float', 'int', - 'long', 'object', 'operator', 'regex', 'sbyte', 'short', 'single', 'string', - 'timespan', 'uint', 'ulong', 'ushort' -}) +lex:add_rule('type', token(lexer.TYPE, word_match{ + 'bool', 'byte', 'char', 'date', 'decimal', 'double', 'duck', 'float', 'int', 'long', 'object', + 'operator', 'regex', 'sbyte', 'short', 'single', 'string', 'timespan', 'uint', 'ulong', 'ushort' +})) -- Functions. -local func = token(l.FUNCTION, word_match{ - 'array', 'assert', 'checked', 'enumerate', '__eval__', 'filter', 'getter', - 'len', 'lock', 'map', 'matrix', 'max', 'min', 'normalArrayIndexing', 'print', - 'property', 'range', 'rawArrayIndexing', 'required', '__switch__', 'typeof', - 'unchecked', 'using', 'yieldAll', 'zip' -}) +lex:add_rule('function', token(lexer.FUNCTION, word_match{ + 'array', 'assert', 'checked', 'enumerate', '__eval__', 'filter', 'getter', 'len', 'lock', 'map', + 'matrix', 'max', 'min', 'normalArrayIndexing', 'print', 'property', 'range', 'rawArrayIndexing', + 'required', '__switch__', 'typeof', 'unchecked', 'using', 'yieldAll', 'zip' +})) -- Identifiers. -local identifier = token(l.IDENTIFIER, l.word) +lex:add_rule('identifier', token(lexer.IDENTIFIER, lexer.word)) --- Operators. -local operator = token(l.OPERATOR, S('!%^&*()[]{}-=+/|:;.,?<>~`')) +-- Strings. +local sq_str = lexer.range("'", true) +local dq_str = lexer.range('"', true) +local tq_str = lexer.range('"""') +local string = token(lexer.STRING, tq_str + sq_str + dq_str) +local regex_str = #P('/') * lexer.last_char_includes('!%^&*([{-=+|:;,?<>~') * lexer.range('/', true) +local regex = token(lexer.REGEX, regex_str) +lex:add_rule('string', string + regex) + +-- Comments. +local line_comment = lexer.to_eol('#', true) +local block_comment = lexer.range('/*', '*/') +lex:add_rule('comment', token(lexer.COMMENT, line_comment + block_comment)) -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'type', type}, - {'function', func}, - {'identifier', identifier}, - {'string', string}, - {'comment', comment}, - {'number', number}, - {'operator', operator}, -} +-- Numbers. +lex:add_rule('number', token(lexer.NUMBER, lexer.number * (S('msdhsfFlL') + 'ms')^-1)) + +-- Operators. +lex:add_rule('operator', token(lexer.OPERATOR, S('!%^&*()[]{}-=+/|:;.,?<>~`'))) -return M +return lex |
