diff options
Diffstat (limited to 'lua/lexers/nemerle.lua')
| -rw-r--r-- | lua/lexers/nemerle.lua | 112 |
1 files changed, 48 insertions, 64 deletions
diff --git a/lua/lexers/nemerle.lua b/lua/lexers/nemerle.lua index ee7c38a..96feb51 100644 --- a/lua/lexers/nemerle.lua +++ b/lua/lexers/nemerle.lua @@ -1,81 +1,65 @@ --- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE. +-- Copyright 2006-2022 Mitchell. See LICENSE. -- Nemerle 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 = 'nemerle'} +local lex = lexer.new('nemerle') -- 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 = P('L')^-1 * l.delimited_range("'", true) -local dq_str = P('L')^-1 * l.delimited_range('"', true) -local string = token(l.STRING, sq_str + dq_str) - --- Numbers. -local number = token(l.NUMBER, l.float + l.integer) - --- Preprocessor. -local preproc_word = word_match{ - 'define', 'elif', 'else', 'endif', 'endregion', 'error', 'if', 'ifdef', - 'ifndef', 'line', 'pragma', 'region', 'undef', 'using', 'warning' -} -local preproc = token(l.PREPROCESSOR, - l.starts_line('#') * S('\t ')^0 * preproc_word) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1)) -- Keywords. -local keyword = token(l.KEYWORD, word_match{ - '_', 'abstract', 'and', 'array', 'as', 'base', 'catch', 'class', 'def', 'do', - 'else', 'extends', 'extern', 'finally', 'foreach', 'for', 'fun', 'if', - 'implements', 'in', 'interface', 'internal', 'lock', 'macro', 'match', - 'module', 'mutable', 'namespace', 'new', 'out', 'override', 'params', - 'private', 'protected', 'public', 'ref', 'repeat', 'sealed', 'static', - 'struct', 'syntax', 'this', 'throw', 'try', 'type', 'typeof', 'unless', - 'until', 'using', 'variant', 'virtual', 'when', 'where', 'while', +lex:add_rule('keyword', token(lexer.KEYWORD, word_match{ + '_', 'abstract', 'and', 'array', 'as', 'base', 'catch', 'class', 'def', 'do', 'else', 'extends', + 'extern', 'finally', 'foreach', 'for', 'fun', 'if', 'implements', 'in', 'interface', 'internal', + 'lock', 'macro', 'match', 'module', 'mutable', 'namespace', 'new', 'out', 'override', 'params', + 'private', 'protected', 'public', 'ref', 'repeat', 'sealed', 'static', 'struct', 'syntax', 'this', + 'throw', 'try', 'type', 'typeof', 'unless', 'until', 'using', 'variant', 'virtual', 'when', + 'where', 'while', -- Values. 'null', 'true', 'false' -}) +})) -- Types. -local type = token(l.TYPE, word_match{ - 'bool', 'byte', 'char', 'decimal', 'double', 'float', 'int', 'list', 'long', - 'object', 'sbyte', 'short', 'string', 'uint', 'ulong', 'ushort', 'void' -}) +lex:add_rule('type', token(lexer.TYPE, word_match{ + 'bool', 'byte', 'char', 'decimal', 'double', 'float', 'int', 'list', 'long', 'object', 'sbyte', + 'short', 'string', 'uint', 'ulong', 'ushort', 'void' +})) + +-- Strings. +local sq_str = P('L')^-1 * lexer.range("'", true) +local dq_str = P('L')^-1 * lexer.range('"', true) +lex:add_rule('string', token(lexer.STRING, sq_str + dq_str)) -- 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)) + +-- Numbers. +lex:add_rule('number', token(lexer.NUMBER, lexer.number)) + +-- Preprocessor. +lex:add_rule('preproc', token(lexer.PREPROCESSOR, lexer.starts_line('#') * S('\t ')^0 * word_match{ + 'define', 'elif', 'else', 'endif', 'endregion', 'error', 'if', 'ifdef', 'ifndef', 'line', + 'pragma', 'region', 'undef', 'using', 'warning' +})) -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'type', type}, - {'identifier', identifier}, - {'string', string}, - {'comment', comment}, - {'number', number}, - {'preproc', preproc}, - {'operator', operator}, -} +-- Operators. +lex:add_rule('operator', token(lexer.OPERATOR, S('+-/*%<>!=^&|?~:;.()[]{}'))) -M._foldsymbols = { - _patterns = {'%l+', '[{}]', '/%*', '%*/', '//'}, - [l.PREPROCESSOR] = { - region = 1, endregion = -1, - ['if'] = 1, ifdef = 1, ifndef = 1, endif = -1 - }, - [l.OPERATOR] = {['{'] = 1, ['}'] = -1}, - [l.COMMENT] = {['/*'] = 1, ['*/'] = -1, ['//'] = l.fold_line_comments('//')} -} +-- Fold points. +lex:add_fold_point(lexer.PREPROCESSOR, 'region', 'endregion') +lex:add_fold_point(lexer.PREPROCESSOR, 'if', 'endif') +lex:add_fold_point(lexer.PREPROCESSOR, 'ifdef', 'endif') +lex:add_fold_point(lexer.PREPROCESSOR, 'ifndef', 'endif') +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 |
