This file is indexed.

/usr/share/perl5/CQL/Lexer.pm is in libcql-parser-perl 1.10-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
package CQL::Lexer;

use strict;
use warnings;
use Carp qw( croak );
use String::Tokenizer;
use CQL::Token;

=head1 NAME

CQL::Lexer - a lexical analyzer for CQL

=head1 SYNOPSIS

    my $lexer = CQL::Lexer->new();
    $lexer->tokenize( 'foo and bar' );
    my @tokens = $lexer->getTokens();

=head1 DESCRIPTION

CQL::Lexer is lexical analyzer for a string of CQL. Once you've
got a CQL::Lexer object you can tokenize a CQL string into CQL::Token
objects. Ordinarily you'll never want to do this yourself since
CQL::Parser calls CQL::Lexer for you.

CQL::Lexer uses Stevan Little's lovely String::Tokenizer in the background,
and does a bit of analysis afterwards to handle some peculiarities of 
CQL: double quoted strings, <, <=, etc.

=head1 METHODS

=head2 new()

The constructor. 

=cut

sub new {
    my $class = shift;
    my $self = { 
        tokenizer   => String::Tokenizer->new(),
        tokens      => [],
        position    => 0,
    };
    return bless $self, ref($class) || $class;
}

=head2 tokenize()

Pass in a string of CQL to tokenize. This initializes the lexer with 
data so that you can retrieve tokens.

=cut

sub tokenize {
    my ( $self, $string ) = @_;

    ## extract the String::Tokenizer object we will use
    my $tokenizer = $self->{tokenizer};

    ## reset position parsing a new string of tokens
    $self->reset();

    ## delegate to String::Tokenizer for basic tokenization
    debug( "tokenizing: $string" );
    $tokenizer->tokenize( $string, '\/<>=()"',
        String::Tokenizer->RETAIN_WHITESPACE );

    ## do a bit of lexical analysis on the results of basic
    debug( "lexical analysis on tokens" );
    my @tokens = _analyze( $tokenizer );
    $self->{tokens} = \@tokens;
}

=head2 getTokens()

Returns a list of all the tokens.

=cut

sub getTokens {
    my $self = shift;
    return @{ $self->{tokens} };
}

=head2 token() 

Returns the current token.

=cut

sub token {
    my $self = shift;
    return $self->{tokens}[ $self->{position} ];
}

=head2 nextToken()

Returns the next token, or undef if there are more tokens to retrieve
from the lexer.

=cut

sub nextToken {
    my $self = shift;
    ## if we haven't gone over the end of our token list
    ## return the token at our current position while
    ## incrementing the position.
    if ( $self->{position} < @{ $self->{tokens} } ) {
        my $token = $self->{tokens}[ $self->{position}++ ];
        return $token;
    }
    return CQL::Token->new( '' );
}

=head2 prevToken()

Returns the previous token, or undef if there are no tokens prior
to the current token.

=cut

sub prevToken {
    my $self = shift;
    ## if we're not at the start of our list of tokens
    ## return the one previous to our current position
    ## while decrementing our position.
    if ( $self->{position} > 0 ) {
        my $token = $self->{tokens}[ --$self->{position} ];
        return $token;
    }
    return CQL::Token->new( '' );
}

=head2 reset()

Resets the iterator to start reading tokens from the beginning.

=cut

sub reset {
    shift->{position} = 0;
}

## Private sub used by _analyze for collecting a backslash escaped string terminated by "
sub _getString {
    my $iterator = shift;
    my $string = '"';
    my $escaping = 0;
    # loop through the tokens untill an unescaped " found
    while ($iterator->hasNextToken()) {
        my $token = $iterator->nextToken();
        $string .= $token;
        if ($escaping) {
        	$escaping = 0;
        } elsif ($token eq '"') {       
        	return $string;
        } elsif ($token eq "\\") {
        	$escaping = 1;
        }
    }
    croak( 'unterminated string ' . $string);
}

## Private sub used by _analyze to process \ outside double quotes.
## Because we tokenized on \ any \ outside double quotes (inside is handled by _getString)
## might need to be concatenated with a previous and or next CQL_WORD to form one CQL_WORD token
sub _concatBackslash {
	my $tokensRef = shift;
    my $i = 0;
    while ($i < @$tokensRef) {
    	my $token = $$tokensRef[$i];
    	if ($token->getString() eq "\\") {
    		my $s = "\\";
    		my $replace = 0;
    		if ($i > 0) {
    			my $prevToken = $$tokensRef[$i - 1];
    			if (($prevToken->getType() == CQL_WORD) and !$prevToken->{terminated}) {
    				# concatenate and delete the previous CQL_WORD token
    				$s = $prevToken->getString() . $s;
    				$i--;
    				splice @$tokensRef, $i, 1;
    				$replace = 1;
    			}
    		}
    		if (!$token->{terminated} and ($i < $#$tokensRef)) {
    			my $nextToken = $$tokensRef[$i + 1];
    			if ($nextToken->getType() == CQL_WORD) {
    				# concatenate and delete the next CQL_WORD token
    				$s .= $nextToken->getString();
    				splice @$tokensRef, $i + 1, 1;
    				$replace = 1;
    			}
    		}
    		if ($replace) {
    			$$tokensRef[$i] = CQL::Token->new($s);
    		}
    	}
    	$i++;
    }
}

sub _analyze { 
    my $tokenizer = shift;

    my $iterator = $tokenizer->iterator();
    my @tokens;
    while ( defined (my $token = $iterator->nextToken()) ) {

        ## <=
        if ( $token eq '<' and $iterator->lookAheadToken() eq '=' ) {
            push( @tokens, CQL::Token->new( '<=' ) );
            $iterator->nextToken();
        } 

        ## <>
        elsif ( $token eq '<' and $iterator->lookAheadToken() eq '>' ) {
            push( @tokens, CQL::Token->new( '<>') );
            $iterator->nextToken();
        }

        ## >=
        elsif ( $token eq '>' and $iterator->lookAheadToken() eq '=' ) {
            push( @tokens, CQL::Token->new( '>=' ) );
            $iterator->nextToken();
        }

        ## "quoted strings"
        elsif ( $token eq '"' ) {
        	my $cqlToken = CQL::Token->new( _getString($iterator) );
        	## Mark this and the previous token as terminated to prevent concatenation with backslash
        	$cqlToken->{terminated} = 1;
        	if (@tokens) { $tokens[$#tokens]->{terminated} = 1; }
            push( @tokens, $cqlToken );
        }

        ## if it's just whitespace we can zap it
        elsif ( $token =~ /\s+/ ) { 
            ## Mark the previous token as terminated to prevent concatenation with backslash
            if (@tokens) {
            	$tokens[$#tokens]->{terminated} = 1;
            }
        }

        ## otherwise it's fine the way it is 
        else {
            push( @tokens, CQL::Token->new($token) );
        }
	        
    } # while
    
    ## Concatenate \ outside double quotes with a previous and or next CQL_WORD to form one CQL_WORD token
    _concatBackslash(\@tokens);
    
    return @tokens;
}

sub debug {
    return unless $CQL::DEBUG;
    print STDERR 'CQL::Lexer: ', shift, "\n";
}

1;