File Coverage

blib/lib/MarpaX/Languages/ECMAScript/AST/Grammar/CharacterClasses.pm

Criterion	Covered	Total	%
statement	82	122	67.2
branch			n/a
condition			n/a
subroutine	61	101	60.4
pod	96	96	100.0
total	239	319	74.9

use strict;
use warnings FATAL => 'all';

package MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses;
use Exporter 'import';
use Encode qw/decode/;

# ABSTRACT: ECMAScript, character classes

our $VERSION = '0.019'; # VERSION


our @EXPORT_OK = qw/
BOM
BS
CR
FF
Isb
IsBackslash
IsBOM
IsCaret
IsCR
IsDecimalDigit
IsDollar
IsDot
IsDquote
IseOrE
Ise
IsE
IsEight
IsEscapeCharacter
IsExponentIndicator
Isf
IsFF
IsHexDigit
IsIdentityEscape
IsLbracket
IsLcurly
IsLF
IsLineTerminator
IsLparen
IsLS
IsMinus
Isn
IsNBSP
IsNine
IsNonZeroDigit
IsNULL
IsOctalDigit
IsPatternCharacter
IsPipe
IsPlus
IsPS
IsQuestion_Mark
Isr
IsRbracket
IsRcurly
IsRegularExpressionNonTerminator
IsRegularExpressionNonTerminatorButNotOneOfBackslashOrSlashOrLbracket
IsRegularExpressionNonTerminatorButNotOneOfRbracketOrBackslash
IsRegularExpressionNonTerminatorButNotOneOfStarOrBackslashOrSlashOrLbracket
IsRparen
IsSingleEscapeCharacter
IsSlash
IsSourceCharacter
IsSourceCharacterButNotLineTerminator
IsSourceCharacterButNotOneOfBackslashOrRbracketOrMinus
IsSourceCharacterButNotOneOfDquoteOrBackslashOrLineTerminator
IsSourceCharacterButNotOneOfDquoteOrBackslashOrU0000ThroughU001F
IsSourceCharacterButNotOneOfEscapeCharacterOrLineTerminator
IsSourceCharacterButNotOneOfSlashOrStar
IsSourceCharacterButNotOneOfSlashOrStarOrLineTerminator
IsSourceCharacterButNotOneOfSquoteOrBackslashOrLineTerminator
IsSourceCharacterButNotSlash
IsSourceCharacterButNotStar
IsSourceCharacterButNotStarOrLineTerminator
IsSP
IsSquote
IsStar
Ist
IsTAB
Isu
IsU0000ThroughU001F
IsUnderscore
IsUnicodeCombiningMark
IsUnicodeConnectorPunctuation
IsUnicodeDigit
IsUnicodeLetter
IsUSP
Isv
IsVT
IsWhiteSpace
Isx
IsZero
IsZeroToThree
IsFourToSeven
IsZWJ
IsZWNJ
LineTerminator
LF
LS
NBSP
NULL
PS
SP
TAB
USP
VT
WhiteSpace
/;
our %EXPORT_TAGS = ('all' => \@EXPORT_OK);

our $STAR            = sprintf('%x', ord('*'));
our $SLASH           = sprintf('%x', ord('/'));
our $BACKSLASH       = sprintf('%x', ord('\\'));
our $DQUOTE          = sprintf('%x', ord('"'));
our $SQUOTE          = sprintf('%x', ord("'"));
our $a               = sprintf('%x', ord('a'));
our $b               = sprintf('%x', ord('b'));
our $c               = sprintf('%x', ord('c'));
our $d               = sprintf('%x', ord('d'));
our $e               = sprintf('%x', ord('e'));
our $f               = sprintf('%x', ord('f'));
our $n               = sprintf('%x', ord('n'));
our $r               = sprintf('%x', ord('r'));
our $t               = sprintf('%x', ord('t'));
our $u               = sprintf('%x', ord('u'));
our $v               = sprintf('%x', ord('v'));
our $x               = sprintf('%x', ord('x'));
our $A               = sprintf('%x', ord('A'));
our $B               = sprintf('%x', ord('B'));
our $C               = sprintf('%x', ord('C'));
our $D               = sprintf('%x', ord('D'));
our $E               = sprintf('%x', ord('E'));
our $F               = sprintf('%x', ord('F'));
our $LBRACKET        = sprintf('%x', ord('['));
our $RBRACKET        = sprintf('%x', ord(']'));
our $LPAREN          = sprintf('%x', ord('('));
our $RPAREN          = sprintf('%x', ord(')'));
our $LCURLY          = sprintf('%x', ord('{'));
our $RCURLY          = sprintf('%x', ord('}'));
our $CARET           = sprintf('%x', ord('^'));
our $DOLLAR          = sprintf('%x', ord('$'));
our $UNDERSCORE      = sprintf('%x', ord('_'));
our $DOT             = sprintf('%x', ord('.'));
our $PLUS            = sprintf('%x', ord('+'));
our $QUESTION_MARK   = sprintf('%x', ord('?'));
our $PIPE            = sprintf('%x', ord('|'));
our $MINUS           = sprintf('%x', ord('-'));
our $ZERO            = sprintf('%x', ord('0'));
our $ONE             = sprintf('%x', ord('1'));
our $TWO             = sprintf('%x', ord('2'));
our $THREE           = sprintf('%x', ord('3'));
our $FOUR            = sprintf('%x', ord('4'));
our $FIVE            = sprintf('%x', ord('5'));
our $SIX             = sprintf('%x', ord('6'));
our $SEVEN           = sprintf('%x', ord('7'));
our $EIGHT           = sprintf('%x', ord('8'));
our $NINE            = sprintf('%x', ord('9'));


sub IsWhiteSpace { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsTAB
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsVT
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsFF
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSP
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsNBSP
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBOM
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUSP
END
}


sub WhiteSpace { return [
		     @{TAB()},
		     @{VT()},
		     @{FF()},
		     @{SP()},
		     @{NBSP()},
		     @{BOM()},
		     @{USP()},
		     ];
}


sub IsSourceCharacter { return <
+utf8::Any
END
}


sub IsZWNJ { return <
200C
END
}


sub IsZWJ { return <
200D
END
}


sub IsBOM { return <
FEFF
END
}


sub BOM { return [ "\N{U+FEFF}" ] }


sub BS { return [ "\N{U+0008}" ] }


sub IsTAB { return <
0009
END
}


sub TAB { return [ "\N{U+0009}" ] }


sub IsVT { return <
000B
END
}


sub VT { return [ "\N{U+000B}" ] }


sub IsFF { return <
000C
END
}


sub FF { return [ "\N{U+000C}" ] }


sub IsSP { return <
0020
END
}


sub SP { return [ "\N{U+0020}" ] }


sub IsNBSP { return <
00A0
END
}


sub NBSP { return [ "\N{U+00A0}" ] }


sub IsUSP { return <
+utf8::Zs
END
}


our @USP = ();
{
    #
    # We do as "unichars". And hardcode restriction to 65535, i.e.
    # the maximum supported by ECMAScript
    #
    foreach (0..65535) {
        # gaggy UTF-16 surrogates are invalid UTF-8 code points
        next if ($_ >= 0xD800 && $_ <= 0xDFFF);

        # from utf8.c in perl src; must avoid fatals in 5.10
        next if ($_ >= 0xFDD0 && $_ <= 0xFDEF);

        next if (0xFFFE == ($_ & 0xFFFE)); # both FFFE and FFFF

        # see "Unicode non-character %s is illegal for interchange" in perldiag(1)
        $_ = do { no warnings "utf8"; chr($_) };

        # fixes "the Unicode bug"
        unless (utf8::is_utf8($_)) {
            $_ = decode("iso-8859-1", $_);
        }

	if ($_ =~ /\p{Zs}/) {
	    push(@USP, $_);
	}
    }
}

sub USP { return \@USP }


sub IsLF { return <
000A
END
}


sub LF { return [ "\N{U+000A}" ]; }


sub IsCR { return <
000D
END
}


sub CR { return [ "\N{U+000D}" ]; }


sub IsNULL { return <
0000
END
}


sub NULL { return [ "\N{U+0000}" ]; }


sub IsLS { return <
2028
END
}


sub LS { return [ "\N{U+2028}" ]; }


sub IsPS { return <
2029
END
}


sub PS { return [ "\N{U+2029}" ]; }


sub IsSourceCharacterButNotStar { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
END
}


sub IsSourceCharacterButNotStarOrLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsSourceCharacterButNotOneOfDquoteOrBackslashOrU0000ThroughU001F { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDquote
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsU0000ThroughU001F
END
}


sub IsSourceCharacterButNotOneOfSlashOrStar { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSlash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
END
}


sub IsSourceCharacterButNotSlash { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSlash
END
}


sub IsSourceCharacterButNotOneOfSlashOrStarOrLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSlash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLF
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsCR
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLS
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsPS
END
}


sub LineTerminator { return
			 [
			  @{LF()},
			  @{CR()},
			  @{LS()},
			  @{PS()}
			 ]; }


sub IsSourceCharacterButNotLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsUnicodeLetter { return <
+utf8::Lu
+utf8::Ll
+utf8::Lt
+utf8::Lm
+utf8::Lo
+utf8::Nl
END
}


sub IsUnicodeCombiningMark { return <
+utf8::Mn
+utf8::Mc
END
}


sub IsUnicodeDigit { return <
+utf8::Nd
END
}


sub IsUnicodeConnectorPunctuation { return <
+utf8::Pc
END
}


sub IsU0000ThroughU001F { return <
0000\t001F
END
}


sub IsSourceCharacterButNotOneOfDquoteOrBackslashOrLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDquote
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsSourceCharacterButNotOneOfSquoteOrBackslashOrLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSquote
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsSingleEscapeCharacter { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSquote
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDquote
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isb
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isf
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isn
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isr
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Ist
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isv
END
}

#
# Note: PosixDigit is a perl extension, changed to be coherent with RT #91120
#

sub IsDecimalDigit { return <
$ZERO\t$NINE
END
}


sub IsOctalDigit { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDecimalDigit
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsEight
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsNine
END
}


sub IsNonZeroDigit { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDecimalDigit
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsZero
END
}


sub IsEscapeCharacter { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSingleEscapeCharacter
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDecimalDigit
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isx
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Isu
END
}


sub IsSourceCharacterButNotOneOfEscapeCharacterOrLineTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsEscapeCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsRegularExpressionNonTerminator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLineTerminator
END
}


sub IsRegularExpressionNonTerminatorButNotOneOfStarOrBackslashOrSlashOrLbracket { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRegularExpressionNonTerminator
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSlash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLbracket
END
}


sub IsRegularExpressionNonTerminatorButNotOneOfBackslashOrSlashOrLbracket { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRegularExpressionNonTerminator
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSlash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLbracket
END
}


sub IsRegularExpressionNonTerminatorButNotOneOfRbracketOrBackslash { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRegularExpressionNonTerminator
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRbracket
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
END
}

#
# Note: PosixXDigit is a perl extension, not available before perl-5.12.5 RT #91120
#

sub IsHexDigit { return <
$ZERO\t$NINE
$A\t$F
$a\t$f
END
}


sub IsIdentityEscape { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUnicodeLetter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDollar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUnderscore
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUnicodeCombiningMark
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUnicodeDigit
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsUnicodeConnectorPunctuation
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsZWNJ
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsZWJ
END
}


sub IsExponentIndicator { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Ise
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsE
END
}


sub IsPatternCharacter { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRegularExpressionNonTerminator
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsCaret
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDollar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsDot
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsStar
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsPlus
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsQuestion_Mark
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLparen
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRparen
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLbracket
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRbracket
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsLcurly
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRcurly
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsPipe
END
}


sub IsSourceCharacterButNotOneOfBackslashOrRbracketOrMinus { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsSourceCharacter
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsBackslash
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsRbracket
-MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsMinus
END
}

# -------------------------------------------------------------------


sub Isx { return <
$x
END
}


sub Isu { return <
$u
END
}


sub IsUnderscore { return <
$UNDERSCORE
END
}


sub Isv { return <
$v
END
}


sub IsStar { return <
$STAR
END
}


sub IsBackslash { return <
$BACKSLASH
END
}


sub IsCaret { return <
$CARET
END
}


sub IsDollar { return <
$DOLLAR
END
}


sub IsDot { return <
$DOT
END
}


sub IsLparen { return <
$LPAREN
END
}


sub IsRparen { return <
$RPAREN
END
}


sub IsLcurly { return <
$LCURLY
END
}


sub IsRcurly { return <
$RCURLY
END
}


sub IsQuestion_Mark { return <
$QUESTION_MARK
END
}


sub IsPlus { return <
$PLUS
END
}


sub IsMinus { return <
$MINUS
END
}


sub IsSquote { return <
$SQUOTE
END
}


sub IsDquote { return <
$DQUOTE
END
}


sub IsPipe { return <
$PIPE
END
}


sub IsSlash { return <
$SLASH
END
}


sub IsLbracket { return <
$LBRACKET
END
}


sub IsRbracket { return <
$RBRACKET
END
}



sub Isb { return <
$b
END
}


sub Isf { return <
$f
END
}


sub Ise { return <
$e
END
}


sub IsE { return <
$E
END
}


sub IseOrE { return <
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::Ise
+MarpaX::Languages::ECMAScript::AST::Grammar::CharacterClasses::IsE
END
}


sub Isn { return <
$n
END
}


sub Isr { return <
$r
END
}


sub Ist { return <
$t
END
}


sub IsZero { return <
$ZERO
END
}


sub IsEight { return <
$EIGHT
END
}


sub IsNine { return <
$NINE
END
}


sub IsZeroToThree { return <
$ZERO
$ONE
$TWO
$THREE
END
}


sub IsFourToSeven { return <
$FOUR
$FIVE
$SIX
$SEVEN
END
}


1;

__END__