diff options
Diffstat (limited to 'lua/lexers/javascript.lua')
| -rw-r--r-- | lua/lexers/javascript.lua | 125 |
1 files changed, 75 insertions, 50 deletions
diff --git a/lua/lexers/javascript.lua b/lua/lexers/javascript.lua index 5366298..d94baed 100644 --- a/lua/lexers/javascript.lua +++ b/lua/lexers/javascript.lua @@ -1,65 +1,90 @@ --- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE. +-- Copyright 2006-2022 Mitchell. See LICENSE. -- JavaScript 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 = 'javascript'} +local lex = lexer.new('javascript') -- Whitespace. -local ws = token(l.WHITESPACE, l.space^1) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.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) +-- Keywords. +lex:add_rule('keyword', token(lexer.KEYWORD, word_match{ + 'abstract', 'async', 'await', 'boolean', 'break', 'byte', 'case', 'catch', 'char', 'class', + 'const', 'continue', 'debugger', 'default', 'delete', 'do', 'double', 'else', 'enum', 'export', + 'extends', 'false', 'final', 'finally', 'float', 'for', 'function', 'get', 'goto', 'if', + 'implements', 'import', 'in', 'instanceof', 'int', 'interface', 'let', 'long', 'native', 'new', + 'null', 'of', 'package', 'private', 'protected', 'public', 'return', 'set', 'short', 'static', + 'super', 'switch', 'synchronized', 'this', 'throw', 'throws', 'transient', 'true', 'try', + 'typeof', 'var', 'void', 'volatile', 'while', 'with', 'yield' +})) --- Strings. -local sq_str = l.delimited_range("'") -local dq_str = l.delimited_range('"') -local template_str = l.delimited_range('`') -local regex_str = #P('/') * l.last_char_includes('+-*%^!=&|?:;,([{<>') * - l.delimited_range('/', true) * S('igm')^0 -local string = token(l.STRING, sq_str + dq_str + template_str) + - token(l.REGEX, regex_str) +-- Types. +lex:add_rule('type', token(lexer.TYPE, word_match{ + -- Fundamental objects. + 'Object', 'Function', 'Boolean', 'Symbol', + -- Error Objects. + 'Error', 'AggregateError', 'EvalError', 'InternalError', 'RangeError', 'ReferenceError', + 'SyntaxError', 'TypeError', 'URIError', + -- Numbers and dates. + 'Number', 'BigInt', 'Math', 'Date', + -- Text Processing. + 'String', 'RegExp', + -- Indexed collections. + 'Array', 'Int8Array', 'Uint8Array', 'Uint8ClampedArray', 'Int16Array', 'Uint16Array', + 'Int32Array', 'Uint32Array', 'Float32Array', 'Float64Array', 'BigInt64Array', 'BigUint64Array', + -- Keyed collections. + 'Map', 'Set', 'WeakMap', 'WeakSet', + -- Structured data. + 'ArrayBuffer', 'SharedArrayBuffer', 'Atomics', 'DataView', 'JSON', + -- Control abstraction objects. + 'GeneratorFunction', 'AsyncGeneratorFunction', 'Generator', 'AsyncGenerator', 'AsyncFunction', + 'Promise', + -- Reflection. + 'Reflect', 'Proxy', + -- Other. + 'Intl', 'WebAssembly' +})) --- Numbers. -local number = token(l.NUMBER, l.float + l.integer) +-- Functions. +lex:add_rule('function', token(lexer.FUNCTION, word_match{ + 'eval', 'isFinite', 'isNaN', 'parseFloat', 'parseInt', 'decodeURI', 'decodeURIComponent', + 'encodeURI', 'encodeURIComponent' +})) --- Keywords. -local keyword = token(l.KEYWORD, word_match{ - 'abstract', 'async', 'await', 'boolean', 'break', 'byte', 'case', 'catch', - 'char', 'class', 'const', 'continue', 'debugger', 'default', 'delete', - 'do', 'double', 'else', 'enum', 'export', 'extends', 'false', 'final', - 'finally', 'float', 'for', 'function', 'get', 'goto', 'if', 'implements', - 'import', 'in', 'instanceof', 'int', 'interface', 'let', 'long', 'native', - 'new', 'null', 'of', 'package', 'private', 'protected', 'public', 'return', - 'set', 'short', 'static', 'super', 'switch', 'synchronized', 'this', - 'throw', 'throws', 'transient', 'true', 'try', 'typeof', 'var', 'void', - 'volatile', 'while', 'with', 'yield' -}) +-- Constants. +lex:add_rule('constant', + token(lexer.CONSTANT, word_match('Infinity NaN undefined globalThis arguments'))) -- Identifiers. -local identifier = token(l.IDENTIFIER, l.word) +lex:add_rule('identifier', token(lexer.IDENTIFIER, lexer.word)) --- Operators. -local operator = token(l.OPERATOR, S('+-/*%^!=&|?:;,.()[]{}<>')) +-- Comments. +local line_comment = lexer.to_eol('//', true) +local block_comment = lexer.range('/*', '*/') +lex:add_rule('comment', token(lexer.COMMENT, line_comment + block_comment)) + +-- Strings. +local sq_str = lexer.range("'") +local dq_str = lexer.range('"') +local bq_str = lexer.range('`') +local string = token(lexer.STRING, sq_str + dq_str + bq_str) +local regex_str = + #P('/') * lexer.last_char_includes('+-*%^!=&|?:;,([{<>') * lexer.range('/', true) * S('igm')^0 +local regex = token(lexer.REGEX, regex_str) +lex:add_rule('string', string + regex) -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'identifier', identifier}, - {'comment', comment}, - {'number', number}, - {'string', string}, - {'operator', operator}, -} +-- Numbers. +lex:add_rule('number', token(lexer.NUMBER, lexer.number)) + +-- Operators. +lex:add_rule('operator', token(lexer.OPERATOR, S('+-/*%^!=&|?:;,.()[]{}<>'))) -M._foldsymbols = { - _patterns = {'[{}]', '/%*', '%*/', '//'}, - [l.OPERATOR] = {['{'] = 1, ['}'] = -1}, - [l.COMMENT] = {['/*'] = 1, ['*/'] = -1, ['//'] = l.fold_line_comments('//')} -} +-- Fold points. +lex:add_fold_point(lexer.OPERATOR, '{', '}') +lex:add_fold_point(lexer.COMMENT, '/*', '*/') +lex:add_fold_point(lexer.COMMENT, lexer.fold_consecutive_lines('//')) -return M +return lex |
