/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * See LICENSE.txt included in this distribution for the specific
 * language governing permissions and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at LICENSE.txt.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright (c) 2006, 2016, Oracle and/or its affiliates. All rights reserved.
 * Portions Copyright (c) 2017, Chris Fraire <cfraire@me.com>.
 */

/*
 * id  ::=  plainid
 *      |  ‘`’ { charNoBackQuoteOrNewline | UnicodeEscape | charEscapeSeq } ‘`’
 * plainid ::=  upper idrest
 *          |  varid
 *          |  op
 * varid ::=  lower idrest
 * op  ::=  opchar {opchar}
 */
Identifier = {plainid_mod1}
OpSuffixIdentifier = {plainid_mod2}
OpIdentifier = {op}
BacktickIdentifier = [`] ({charNoBackQuoteOrNewline} | {UnicodeEscape} |
    {charEscapeSeq})+ [`]
plainid_mod1 = ({upper} | {lower}) {idrest_char}*
plainid_mod2 = ({upper} | {lower}) {idrest_char}* "_" {op}
op = {opchar}+
/*
 * opchar ::= // printableChar not matched by (whiteSpace | upper | lower |
 *     // letter | digit | paren | delim)
 * opchar ::= Unicode_Sm | Unicode_So ; N.b. [cfraire] I believe the definition
 *    from 2.12 where the exclusion parenthetical above contains
 *    "opchar | Unicode_Sm | Unicode_So" is a typo and this is the proper form.
 * printableChar ::= // all characters in [\u0020, \u007F] inclusive
 */
opchar = ([[\u{0020}-\u{007F}]--[\sA-Z\$_\p{Lu}a-z\p{Ll}\p{Lo}\p{Lt}\p{Nl}0-9\(\)\[\]\{\}`\'\"\.;,]] |
    [\p{Sm}\p{So}])
/*
 * upper   ::=  ‘A’ | … | ‘Z’ | ‘$’ | ‘_’  // and Unicode category Lu
 * lower   ::=  ‘a’ | … | ‘z’ // and Unicode category Ll
 * idrest  ::=  {letter | digit} [‘_’ op]
 * letter  ::=  upper | lower // and Unicode categories Lo, Lt, Nl
 * UnicodeEscape ::= ‘\’ ‘u’ {‘u’} hexDigit hexDigit hexDigit hexDigit
 * charEscapeSeq    ::= ‘\’ (‘b’ | ‘t’ | ‘n’ | ‘f’ | ‘r’ | ‘"’ | ‘'’ | ‘\’)
 */
upper = [A-Z\$_\p{Lu}]
lower = [a-z\p{Ll}]
idrest_char = ({letter} | {digit}) // N.b. here OpenGrok ignores the op suffix
letter = ({upper} | {lower} | [\p{Lo}\p{Lt}\p{Nl}])
charNoBackQuoteOrNewline = [[^]--[\n\r`]]
UnicodeEscape = \\ [u]+ {hexDigit}{4}
charEscapeSeq = \\ [btnfr\"\'\\]

Number = [\-]? ({integerLiteral} | {floatingPointLiteral})
/*
 * Numeric Literal ::= [‘-’] integerLiteral
 *                  |  [‘-’] floatingPointLiteral
 *
 * integerLiteral  ::=  (decimalNumeral | hexNumeral) [‘L’ | ‘l’]
 * decimalNumeral  ::=  ‘0’ | nonZeroDigit {digit}
 * hexNumeral      ::=  ‘0’ (‘x’ | ‘X’) hexDigit {hexDigit}
 * digit           ::=  ‘0’ | nonZeroDigit
 * nonZeroDigit    ::=  ‘1’ | … | ‘9’
 * hexDigit        ::= ‘0’ | … | ‘9’ | ‘A’ | … | ‘F’ | ‘a’ | … | ‘f’
 */
integerLiteral = ({decimalNumeral} | {hexNumeral}) [Ll]?
decimalNumeral = ([0] | {nonZeroDigit} {digit}*)
hexNumeral = [0][xX] {hexDigit}+
digit = [0-9]
nonZeroDigit = [1-9]
hexDigit = [0-9A-Fa-f]

/*
 * floatingPointLiteral  ::=
 *     digit {digit} ‘.’ digit {digit} [exponentPart] [floatType]
 *     |  ‘.’ digit {digit} [exponentPart] [floatType]
 *     |  digit {digit} exponentPart [floatType]
 *     |  digit {digit} [exponentPart] floatType
 * exponentPart          ::=  (‘E’ | ‘e’) [‘+’ | ‘-’] digit {digit}
 * floatType             ::=  ‘F’ | ‘f’ | ‘D’ | ‘d’
 */
floatingPointLiteral = ({digit}+ "." {digit}+ {exponentPart}? {floatType}? |
    "." {digit}+ {exponentPart}? {floatType}? |
    {digit}+ {exponentPart} {floatType}? |
    {digit}+ {exponentPart}? {floatType})
exponentPart = [Ee] [\+\-]? {digit}+
floatType = [FfDd]