diff options
Diffstat (limited to 'lua/lexers/fsharp.lua')
| -rw-r--r-- | lua/lexers/fsharp.lua | 101 |
1 files changed, 41 insertions, 60 deletions
diff --git a/lua/lexers/fsharp.lua b/lua/lexers/fsharp.lua index 39416a5..18df9bb 100644 --- a/lua/lexers/fsharp.lua +++ b/lua/lexers/fsharp.lua @@ -1,76 +1,57 @@ --- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE. +-- Copyright 2006-2022 Mitchell. See LICENSE. -- F# 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 = 'fsharp'} +local lex = lexer.new('fsharp', {fold_by_indentation = true}) -- Whitespace. -local ws = token(l.WHITESPACE, l.space^1) - --- Comments. -local line_comment = P('//') * l.nonnewline^0 -local block_comment = l.nested_pair('(*', '*)') -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 string = token(l.STRING, sq_str + dq_str) - --- Numbers. -local number = token(l.NUMBER, (l.float + l.integer * S('uUlL')^-1)) - --- Preprocessor. -local preproc_word = word_match{ - 'ifndef', 'ifdef', 'if', 'else', 'endif', 'light', 'region', 'endregion' -} -local preproc = token(l.PREPROCESSOR, - l.starts_line('#') * S('\t ')^0 * preproc_word * - (l.nonnewline_esc^1 + l.space * l.nonnewline_esc^0)) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1)) -- Keywords. -local keyword = token(l.KEYWORD, word_match{ - 'abstract', 'and', 'as', 'assert', 'asr', 'begin', 'class', 'default', - 'delegate', 'do', 'done', 'downcast', 'downto', 'else', 'end', 'enum', - 'exception', 'false', 'finaly', 'for', 'fun', 'function', 'if', 'in', - 'iherit', 'interface', 'land', 'lazy', 'let', 'lor', 'lsl', 'lsr', 'lxor', - 'match', 'member', 'mod', 'module', 'mutable', 'namespace', 'new', 'null', - 'of', 'open', 'or', 'override', 'sig', 'static', 'struct', 'then', 'to', - 'true', 'try', 'type', 'val', 'when', 'inline', 'upcast', 'while', 'with', - 'async', 'atomic', 'break', 'checked', 'component', 'const', 'constructor', - 'continue', 'eager', 'event', 'external', 'fixed', 'functor', 'include', - 'method', 'mixin', 'process', 'property', 'protected', 'public', 'pure', - 'readonly', 'return', 'sealed', 'switch', 'virtual', 'void', 'volatile', - 'where', +lex:add_rule('keyword', token(lexer.KEYWORD, word_match{ + 'abstract', 'and', 'as', 'assert', 'asr', 'begin', 'class', 'default', 'delegate', 'do', 'done', + 'downcast', 'downto', 'else', 'end', 'enum', 'exception', 'false', 'finaly', 'for', 'fun', + 'function', 'if', 'in', 'iherit', 'interface', 'land', 'lazy', 'let', 'lor', 'lsl', 'lsr', 'lxor', + 'match', 'member', 'mod', 'module', 'mutable', 'namespace', 'new', 'null', 'of', 'open', 'or', + 'override', 'sig', 'static', 'struct', 'then', 'to', 'true', 'try', 'type', 'val', 'when', + 'inline', 'upcast', 'while', 'with', 'async', 'atomic', 'break', 'checked', 'component', 'const', + 'constructor', 'continue', 'eager', 'event', 'external', 'fixed', 'functor', 'include', 'method', + 'mixin', 'process', 'property', 'protected', 'public', 'pure', 'readonly', 'return', 'sealed', + 'switch', 'virtual', 'void', 'volatile', 'where', -- Booleans. 'true', 'false' -}) +})) -- Types. -local type = token(l.TYPE, word_match{ - 'bool', 'byte', 'sbyte', 'int16', 'uint16', 'int', 'uint32', 'int64', - 'uint64', 'nativeint', 'unativeint', 'char', 'string', 'decimal', 'unit', - 'void', 'float32', 'single', 'float', 'double' -}) +lex:add_rule('type', token(lexer.TYPE, word_match{ + 'bool', 'byte', 'sbyte', 'int16', 'uint16', 'int', 'uint32', 'int64', 'uint64', 'nativeint', + 'unativeint', 'char', 'string', 'decimal', 'unit', 'void', 'float32', 'single', 'float', 'double' +})) -- 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) +lex:add_rule('string', token(lexer.STRING, sq_str + dq_str)) + +-- Comments. +local line_comment = lexer.to_eol('//') +local block_comment = lexer.range('(*', '*)', false, false, true) +lex:add_rule('comment', token(lexer.COMMENT, line_comment + block_comment)) + +-- Numbers. +lex:add_rule('number', token(lexer.NUMBER, lexer.float + lexer.integer * S('uUlL')^-1)) + +-- Preprocessor. +lex:add_rule('preproc', token(lexer.PREPROCESSOR, lexer.starts_line('#') * S('\t ')^0 * + word_match('else endif endregion if ifdef ifndef light region'))) -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'type', type}, - {'identifier', identifier}, - {'string', string}, - {'comment', comment}, - {'number', number}, - {'operator', operator}, -} +-- Operators. +lex:add_rule('operator', token(lexer.OPERATOR, S('=<>+-*/^.,:;~!@#%^&|?[](){}'))) -return M +return lex |
