1 files changed, 63 insertions, 69 deletions
diff --git a/lua/lexers/fortran.lua b/lua/lexers/fortran.lua
index 87026a7..7d0480f 100644
--- a/lua/lexers/fortran.lua
+++ b/lua/lexers/fortran.lua
@@ -1,91 +1,85 @@
--- Copyright 2006-2017 Mitchell mitchell.att.foicica.com. See LICENSE.
+-- Copyright 2006-2022 Mitchell. See LICENSE.
 -- Fortran 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 = 'fortran'}
+local lex = lexer.new('fortran')
 
 -- Whitespace.
-local ws = token(l.WHITESPACE, l.space^1)
+lex:add_rule('whitespace', token(lexer.WHITESPACE, lexer.space^1))
 
 -- Comments.
-local c_comment = l.starts_line(S('Cc')) * l.nonnewline^0
-local d_comment = l.starts_line(S('Dd')) * l.nonnewline^0
-local ex_comment = l.starts_line('!') * l.nonnewline^0
-local ast_comment = l.starts_line('*') * l.nonnewline^0
-local line_comment = '!' * l.nonnewline^0
-local comment = token(l.COMMENT, c_comment + d_comment + ex_comment +
-                      ast_comment + line_comment)
-
--- Strings.
-local sq_str = l.delimited_range("'", true, true)
-local dq_str = l.delimited_range('"', true, true)
-local string = token(l.STRING, sq_str + dq_str)
-
--- Numbers.
-local number = token(l.NUMBER, (l.float + l.integer) * -l.alpha)
+local line_comment = lexer.to_eol(lexer.starts_line(S('CcDd!*')) + '!')
+lex:add_rule('comment', token(lexer.COMMENT, line_comment))
 
 -- Keywords.
-local keyword = token(l.KEYWORD, word_match({
-  'include', 'program', 'module', 'subroutine', 'function', 'contains', 'use',
-  'call', 'return',
+lex:add_rule('keyword', token(lexer.KEYWORD, word_match({
+  'include', 'interface', 'program', 'module', 'subroutine', 'function', 'contains', 'use', 'call',
+  'return',
   -- Statements.
-  'case', 'select', 'default', 'continue', 'cycle', 'do', 'while', 'else', 'if',
-  'elseif', 'then', 'elsewhere', 'end', 'endif', 'enddo', 'forall', 'where',
-  'exit', 'goto', 'pause', 'stop',
+  'case', 'select', 'default', 'continue', 'cycle', 'do', 'while', 'else', 'if', 'elseif', 'then',
+  'elsewhere', 'end', 'endif', 'enddo', 'equivalence', 'external', 'forall', 'where', 'exit',
+  'goto', 'pause', 'save', 'stop',
   -- Operators.
-  '.not.', '.and.', '.or.', '.xor.', '.eqv.', '.neqv.', '.eq.', '.ne.', '.gt.',
-  '.ge.', '.lt.', '.le.',
+  '.not.', '.and.', '.or.', '.xor.', '.eqv.', '.neqv.', '.eq.', '.ne.', '.gt.', '.ge.', '.lt.',
+  '.le.',
   -- Logical.
-  '.false.', '.true.'
-}, '.', true))
+  '.false.', '.true.',
+  -- Attributes and other keywords.
+  'access', 'action', 'advance', 'assignment', 'block', 'entry', 'in', 'inout', 'intent', 'only',
+  'out', 'optional', 'pointer', 'precision', 'procedure', 'recursive', 'result', 'sequence', 'size',
+  'stat', 'target', 'type'
+}, true)))
 
 -- Functions.
-local func = token(l.FUNCTION, word_match({
+lex:add_rule('function', token(lexer.FUNCTION, word_match({
   -- I/O.
-  'backspace', 'close', 'endfile', 'inquire', 'open', 'print', 'read', 'rewind',
-  'write', 'format',
-  -- Type conversion, utility, and math.
-  'aimag', 'aint', 'amax0', 'amin0', 'anint', 'ceiling', 'cmplx', 'conjg',
-  'dble', 'dcmplx', 'dfloat', 'dim', 'dprod', 'float', 'floor', 'ifix', 'imag',
-  'int', 'logical', 'modulo', 'nint', 'real', 'sign', 'sngl', 'transfer',
-  'zext', 'abs', 'acos', 'aimag', 'aint', 'alog', 'alog10', 'amax0', 'amax1',
-  'amin0', 'amin1', 'amod', 'anint', 'asin', 'atan', 'atan2', 'cabs', 'ccos',
-  'char', 'clog', 'cmplx', 'conjg', 'cos', 'cosh', 'csin', 'csqrt', 'dabs',
-  'dacos', 'dasin', 'datan', 'datan2', 'dble', 'dcos', 'dcosh', 'ddim', 'dexp',
-  'dim', 'dint', 'dlog', 'dlog10', 'dmax1', 'dmin1', 'dmod', 'dnint', 'dprod',
-  'dreal', 'dsign', 'dsin', 'dsinh', 'dsqrt', 'dtan', 'dtanh', 'exp', 'float',
-  'iabs', 'ichar', 'idim', 'idint', 'idnint', 'ifix', 'index', 'int', 'isign',
-  'len', 'lge', 'lgt', 'lle', 'llt', 'log', 'log10', 'max', 'max0', 'max1',
-  'min', 'min0', 'min1', 'mod', 'nint', 'real', 'sign', 'sin', 'sinh', 'sngl',
-  'sqrt', 'tan', 'tanh'
-}, nil, true))
+  'backspace', 'close', 'endfile', 'inquire', 'open', 'print', 'read', 'rewind', 'write', 'format',
+  -- Type conversion utility and math.
+  'aimag', 'aint', 'amax0', 'amin0', 'anint', 'ceiling', 'cmplx', 'conjg', 'dble', 'dcmplx',
+  'dfloat', 'dim', 'dprod', 'float', 'floor', 'ifix', 'imag', 'int', 'logical', 'modulo', 'nint',
+  'real', 'sign', 'sngl', 'transfer', 'zext', 'abs', 'acos', 'aimag', 'aint', 'alog', 'alog10',
+  'amax0', 'amax1', 'amin0', 'amin1', 'amod', 'anint', 'asin', 'atan', 'atan2', 'cabs', 'ccos',
+  'char', 'clog', 'cmplx', 'conjg', 'cos', 'cosh', 'csin', 'csqrt', 'dabs', 'dacos', 'dasin',
+  'datan', 'datan2', 'dble', 'dcos', 'dcosh', 'ddim', 'dexp', 'dim', 'dint', 'dlog', 'dlog10',
+  'dmax1', 'dmin1', 'dmod', 'dnint', 'dprod', 'dreal', 'dsign', 'dsin', 'dsinh', 'dsqrt', 'dtan',
+  'dtanh', 'exp', 'float', 'iabs', 'ichar', 'idim', 'idint', 'idnint', 'ifix', 'index', 'int',
+  'isign', 'len', 'lge', 'lgt', 'lle', 'llt', 'log', 'log10', 'max', 'max0', 'max1', 'min', 'min0',
+  'min1', 'mod', 'nint', 'real', 'sign', 'sin', 'sinh', 'sngl', 'sqrt', 'tan', 'tanh',
+  -- Matrix math.
+  'matmul', 'transpose', 'reshape',
+  -- Other frequently used built-in statements.
+  'assign', 'nullify',
+  -- ISO C binding from Fortran 2003.
+  'c_sizeof', 'c_f_pointer', 'c_associated'
+}, true)))
 
 -- Types.
-local type = token(l.TYPE, word_match({
-  'implicit', 'explicit', 'none', 'data', 'parameter', 'allocate',
-  'allocatable', 'allocated', 'deallocate', 'integer', 'real', 'double',
-  'precision', 'complex', 'logical', 'character', 'dimension', 'kind',
-}, nil, true))
+lex:add_rule('type', token(lexer.TYPE, word_match({
+  'implicit', 'explicit', 'none', 'data', 'parameter', 'allocate', 'allocatable', 'allocated',
+  'deallocate', 'integer', 'real', 'double', 'precision', 'complex', 'logical', 'character',
+  'dimension', 'kind',
+  -- ISO C binding from Fortran 2003
+  'bind', 'c_int', 'c_short', 'c_long', 'c_long_long', 'c_signed_char', 'c_size_t', 'c_int8_t',
+  'c_int16_t', 'c_int32_t', 'c_int64_t', 'c_int128_t', 'c_intptr_t', 'c_float', 'c_double',
+  'c_long_double', 'c_float128', 'c_float_complex', 'c_double_complex', 'c_long_double_complex',
+  'c_float128_complex', 'c_bool', 'c_char', 'c_null_char', 'c_new_line', 'c_null_ptr', 'c_funptr'
+}, true)))
+
+-- Numbers.
+lex:add_rule('number', token(lexer.NUMBER, lexer.number * -lexer.alpha))
 
 -- Identifiers.
-local identifier = token(l.IDENTIFIER, l.alnum^1)
+lex:add_rule('identifier', token(lexer.IDENTIFIER, lexer.alnum^1))
 
--- Operators.
-local operator = token(l.OPERATOR, S('<>=&+-/*,()'))
+-- Strings.
+local sq_str = lexer.range("'", true, false)
+local dq_str = lexer.range('"', true, false)
+lex:add_rule('string', token(lexer.STRING, sq_str + dq_str))
 
-M._rules = {
-  {'whitespace', ws},
-  {'comment', comment},
-  {'keyword', keyword},
-  {'function', func},
-  {'type', type},
-  {'number', number},
-  {'identifier', identifier},
-  {'string', string},
-  {'operator', operator},
-}
+-- Operators.
+lex:add_rule('operator', token(lexer.OPERATOR, S('<>=&+-/*,()')))
 
-return M
+return lex