diff options
Diffstat (limited to 'lua/lexers/pascal.lua')
| -rw-r--r-- | lua/lexers/pascal.lua | 106 |
1 files changed, 45 insertions, 61 deletions
diff --git a/lua/lexers/pascal.lua b/lua/lexers/pascal.lua index fab4bdb..05e9f62 100644 --- a/lua/lexers/pascal.lua +++ b/lua/lexers/pascal.lua @@ -1,78 +1,62 @@ --- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE. +-- Copyright 2006-2022 Mitchell. See LICENSE. -- Pascal 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 = 'pascal'} +local lex = lexer.new('pascal') -- Whitespace. -local ws = token(l.WHITESPACE, l.space^1) - --- Comments. -local line_comment = '//' * l.nonnewline_esc^0 -local bblock_comment = '{' * (l.any - '}')^0 * P('}')^-1 -local pblock_comment = '(*' * (l.any - '*)')^0 * P('*)')^-1 -local comment = token(l.COMMENT, line_comment + bblock_comment + pblock_comment) - --- Strings. -local string = token(l.STRING, S('uUrR')^-1 * - l.delimited_range("'", true, true)) - --- Numbers. -local number = token(l.NUMBER, (l.float + l.integer) * S('LlDdFf')^-1) +lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1)) -- Keywords. -local keyword = token(l.KEYWORD, word_match({ - 'and', 'array', 'as', 'at', 'asm', 'begin', 'case', 'class', 'const', - 'constructor', 'destructor', 'dispinterface', 'div', 'do', 'downto', 'else', - 'end', 'except', 'exports', 'file', 'final', 'finalization', 'finally', 'for', - 'function', 'goto', 'if', 'implementation', 'in', 'inherited', - 'initialization', 'inline', 'interface', 'is', 'label', 'mod', 'not', - 'object', 'of', 'on', 'or', 'out', 'packed', 'procedure', 'program', - 'property', 'raise', 'record', 'repeat', 'resourcestring', 'set', 'sealed', - 'shl', 'shr', 'static', 'string', 'then', 'threadvar', 'to', 'try', 'type', - 'unit', 'unsafe', 'until', 'uses', 'var', 'while', 'with', 'xor', - 'absolute', 'abstract', 'assembler', 'automated', 'cdecl', 'contains', - 'default', 'deprecated', 'dispid', 'dynamic', 'export', 'external', 'far', - 'forward', 'implements', 'index', 'library', 'local', 'message', 'name', - 'namespaces', 'near', 'nodefault', 'overload', 'override', 'package', - 'pascal', 'platform', 'private', 'protected', 'public', 'published', 'read', - 'readonly', 'register', 'reintroduce', 'requires', 'resident', 'safecall', - 'stdcall', 'stored', 'varargs', 'virtual', 'write', 'writeln', 'writeonly', +lex:add_rule('keyword', token(lexer.KEYWORD, word_match({ + 'and', 'array', 'as', 'at', 'asm', 'begin', 'case', 'class', 'const', 'constructor', 'destructor', + 'dispinterface', 'div', 'do', 'downto', 'else', 'end', 'except', 'exports', 'file', 'final', + 'finalization', 'finally', 'for', 'function', 'goto', 'if', 'implementation', 'in', 'inherited', + 'initialization', 'inline', 'interface', 'is', 'label', 'mod', 'not', 'object', 'of', 'on', 'or', + 'out', 'packed', 'procedure', 'program', 'property', 'raise', 'record', 'repeat', + 'resourcestring', 'set', 'sealed', 'shl', 'shr', 'static', 'string', 'then', 'threadvar', 'to', + 'try', 'type', 'unit', 'unsafe', 'until', 'uses', 'var', 'while', 'with', 'xor', 'absolute', + 'abstract', 'assembler', 'automated', 'cdecl', 'contains', 'default', 'deprecated', 'dispid', + 'dynamic', 'export', 'external', 'far', 'forward', 'implements', 'index', 'library', 'local', + 'message', 'name', 'namespaces', 'near', 'nodefault', 'overload', 'override', 'package', 'pascal', + 'platform', 'private', 'protected', 'public', 'published', 'read', 'readonly', 'register', + 'reintroduce', 'requires', 'resident', 'safecall', 'stdcall', 'stored', 'varargs', 'virtual', + 'write', 'writeln', 'writeonly', -- 'false', 'nil', 'self', 'true' -}, nil, true)) +}, true))) -- Functions. -local func = token(l.FUNCTION, word_match({ - 'chr', 'ord', 'succ', 'pred', 'abs', 'round', 'trunc', 'sqr', 'sqrt', - 'arctan', 'cos', 'sin', 'exp', 'ln', 'odd', 'eof', 'eoln' -}, nil, true)) +lex:add_rule('function', token(lexer.FUNCTION, word_match({ + 'chr', 'ord', 'succ', 'pred', 'abs', 'round', 'trunc', 'sqr', 'sqrt', 'arctan', 'cos', 'sin', + 'exp', 'ln', 'odd', 'eof', 'eoln' +}, true))) -- Types. -local type = token(l.TYPE, word_match({ - 'shortint', 'byte', 'char', 'smallint', 'integer', 'word', 'longint', - 'cardinal', 'boolean', 'bytebool', 'wordbool', 'longbool', 'real', 'single', - 'double', 'extended', 'comp', 'currency', 'pointer' -}, nil, true)) +lex:add_rule('type', token(lexer.TYPE, word_match({ + 'shortint', 'byte', 'char', 'smallint', 'integer', 'word', 'longint', 'cardinal', 'boolean', + 'bytebool', 'wordbool', 'longbool', 'real', 'single', 'double', 'extended', 'comp', 'currency', + 'pointer' +}, true))) + +-- Strings. +lex:add_rule('string', token(lexer.STRING, S('uUrR')^-1 * lexer.range("'", true, false))) -- 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 bblock_comment = lexer.range('{', '}') +local pblock_comment = lexer.range('(*', '*)') +lex:add_rule('comment', token(lexer.COMMENT, line_comment + bblock_comment + pblock_comment)) -M._rules = { - {'whitespace', ws}, - {'keyword', keyword}, - {'function', func}, - {'type', type}, - {'string', string}, - {'identifier', identifier}, - {'comment', comment}, - {'number', number}, - {'operator', operator}, -} +-- Numbers. +lex:add_rule('number', token(lexer.NUMBER, lexer.number * S('LlDdFf')^-1)) + +-- Operators. +lex:add_rule('operator', token(lexer.OPERATOR, S('.,;^@:=<>+-/*()[]'))) -return M +return lex |
