diff options
Diffstat (limited to 'lexers/boo.lua')
| -rw-r--r-- | lexers/boo.lua | 81 |
1 files changed, 81 insertions, 0 deletions
diff --git a/lexers/boo.lua b/lexers/boo.lua new file mode 100644 index 0000000..54ad1a6 --- /dev/null +++ b/lexers/boo.lua @@ -0,0 +1,81 @@ +-- Copyright 2006-2015 Mitchell mitchell.att.foicica.com. 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 M = {_NAME = '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) + +-- 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', + -- 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', + -- 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' +}) + +-- 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' +}) + +-- Identifiers. +local identifier = token(l.IDENTIFIER, l.word) + +-- Operators. +local operator = token(l.OPERATOR, S('!%^&*()[]{}-=+/|:;.,?<>~`')) + +M._rules = { + {'whitespace', ws}, + {'keyword', keyword}, + {'type', type}, + {'function', func}, + {'identifier', identifier}, + {'string', string}, + {'comment', comment}, + {'number', number}, + {'operator', operator}, +} + +return M |
