AtteanX/Parser/SPARQLLex.pm

filter: Statementstmt 74.7% 356 / 476 Branchbran 61.2% 131 / 214 Conditioncond 41.1% 21 / 51 MC/DCmcdc 26.4% 9 / 34 Subroutinesub 90.4% 57 / 63 Podpod 33.3% 6 / 18 totaltotal 67.7% 580 / 856 CC 128 SCAR 34.5
CC
128
Cov
69%
_get_iriref_or_relational
156.2
_get_escaped_char
48.1
_get_comment
30.0
CRAP 31.6
« AtteanX/Serializer/TurtleTokens.pm ↑ Summary AtteanX/Parser/SPARQLXML/SAXHandler.pm »
1 13 ▶use v5.14;
Subroutine BEGIN: called CC=1 SCAR=0.0
2 13 ▶use warnings;
Subroutine BEGIN: called CC=1 SCAR=0.0
3  
4 =head1 NAME
5  
6 AtteanX::Parser::SPARQLLex - SPARQL Lexer
7  
8 =head1 VERSION
9  
10 This document describes AtteanX::Parser::SPARQLLex version 0.040
11  
12 =head1 SYNOPSIS
13  
14 use Attean;
15  
16 =head1 DESCRIPTION
17  
18 ...
19  
20 =head1 ATTRIBUTES
21  
22 =over 4
23  
24 =item C<< canonical_media_type >>
25  
26 =item C<< media_types >>
27  
28 =item C<< file_extensions >>
29  
30 =item C<< handled_type >>
31  
32 =item C<< extend >>
33  
34 =back
35  
36 =head1 METHODS
37  
38 =over 4
39  
40 =cut
41  
42 13 package AtteanX::Parser::SPARQLLex 0.040 {
43 13 ▶ use utf8;
Subroutine BEGIN: called CC=1 SCAR=0.0
44 13 ▶ use Moo;
Subroutine BEGIN: called CC=1 SCAR=0.0
45 13 ▶ use Attean;
Subroutine BEGIN: called CC=1 SCAR=0.0
46 13 ▶ use Encode;
Subroutine BEGIN: called CC=1 SCAR=0.0
47 13 ▶ use Encode qw(decode);
Subroutine BEGIN: called CC=1 SCAR=0.0
48 13 ▶ use Types::Standard qw(ArrayRef Str);
Subroutine BEGIN: called CC=1 SCAR=0.0
49 13 ▶ use namespace::clean;
Subroutine BEGIN: called CC=1 SCAR=0.0
50  
51 1 ▶ sub canonical_media_type { return "application/x-sparql-query-tokens" }
Subroutine canonical_media_type: called CC=1 SCAR=0.0
Pod documented
52  
53 # these pass through to the lexer iterator
54 118 ▶ has extend => ( is => 'ro', isa => ArrayRef, default => sub { [] } );
Subroutine __ANON__: called CC=1 SCAR=0.0
55 13 has 'version' => (is => 'rw', isa => Str, default => '1.2');
56  
57 3 ▶ sub media_types {
Subroutine media_types: called CC=1 SCAR=0.0
Pod documented
58 3 return [qw(application/x-sparql-query-tokens)];
59 }
60
61 2 ▶ sub handled_type {
Subroutine handled_type: called CC=1 SCAR=0.0
Pod documented
62 2 state $ITEM_TYPE = Type::Tiny::Role->new(role => 'AtteanX::SPARQL::Token');
63 2 return $ITEM_TYPE;
64 }
65  
66 =item C<< file_extensions >>
67  
68 Returns a list of file extensions that may be parsed with the parser.
69  
70 =cut
71  
72 4 ▶ sub file_extensions { return [qw(rq)] }
Subroutine file_extensions: called CC=1 SCAR=0.0
Pod documented
73  
74 13 with 'Attean::API::PullParser', 'Attean::API::Parser';
75  
76 =item C<< parse_iter_from_bytes( $data ) >>
77  
78 Returns an iterator of SPARQL tokens that result from parsing
79 the SPARQL query/update read from the UTF-8 encoded byte string C<< $data >>.
80  
81 =cut
82  
83 57 ▶ sub parse_iter_from_bytes {
Subroutine parse_iter_from_bytes: called CC=1 SCAR=0.0
Pod documented
84 57 my $self = shift;
85 57 my $data = shift;
86 57 open(my $fh, '<:encoding(UTF-8)', \$data);
87 57 return $self->parse_iter_from_io($fh);
88 }
89  
90 =item C<< parse_iter_from_io( $fh ) >>
91  
92 Returns an iterator of SPARQL tokens that result from parsing
93 the SPARQL query/update read from the L<IO::Handle> object C<< $fh >>.
94  
95 =cut
96  
97 67 ▶ sub parse_iter_from_io {
Subroutine parse_iter_from_io: called CC=1 SCAR=0.0
Pod documented
98 67 my $self = shift;
99 67 my $fh = shift;
100 67 return AtteanX::Parser::SPARQLLex::Iterator->new(
101 extend => $self->extend,
102 file => $fh,
103 version => $self->version,
104 );
105 }
106 }
107  
108 13 package AtteanX::Parser::SPARQLLex::Iterator 0.040 {
109 13 ▶ use utf8;
Subroutine BEGIN: called CC=1 SCAR=0.0
110 13 ▶ use Moo;
Subroutine BEGIN: called CC=1 SCAR=0.0
111 13 ▶ use Attean;
Subroutine BEGIN: called CC=1 SCAR=0.0
112 13 ▶ use Encode;
Subroutine BEGIN: called CC=1 SCAR=0.0
113 13 ▶ use Encode qw(decode);
Subroutine BEGIN: called CC=1 SCAR=0.0
114 13 ▶ use AtteanX::SPARQL::Token;
Subroutine BEGIN: called CC=1 SCAR=0.0
115 13 ▶ use AtteanX::SPARQL::Constants;
Subroutine BEGIN: called CC=1 SCAR=0.0
116 13 ▶ use Types::Standard qw(FileHandle Ref Str Int ArrayRef HashRef ConsumerOf InstanceOf);
Subroutine BEGIN: called CC=1 SCAR=0.0
117 13 ▶ use namespace::clean;
Subroutine BEGIN: called CC=1 SCAR=0.0
118
119 67 ▶ has lookahead_methods => ( is => 'ro', isa => HashRef, default => sub { +{} } );
Subroutine __ANON__: called CC=1 SCAR=0.0
120 67 ▶ has lookahead_tokens => ( is => 'ro', isa => HashRef, default => sub { +{} } );
Subroutine __ANON__: called CC=1 SCAR=0.0
121 0 ▶ has extend => ( is => 'ro', isa => ArrayRef, default => sub { [] } );
Subroutine __ANON__: not called CC=1 SCAR=1.2
122 67 ▶ has token_buffer => ( is => 'ro', isa => ArrayRef, default => sub { [] } );
Subroutine __ANON__: called CC=1 SCAR=0.0
123 13 has 'version' => (is => 'rw', isa => Str, default => '1.2');
124
125 13 with 'AtteanX::API::Lexer';
126
127 13 my $r_ECHAR = qr/\\([tbnrf\\"'])/o;
128 13 my $r_STRING_LITERAL1 = qr/'(([^\x{27}\x{5C}\x{0A}\x{0D}])|${r_ECHAR})*'/o;
129 13 my $r_STRING_LITERAL2 = qr/"(([^\x{22}\x{5C}\x{0A}\x{0D}])|${r_ECHAR})*"/o;
130 13 my $r_STRING_LITERAL_LONG1 = qr/'''(('|'')?([^'\\]|${r_ECHAR}))*'''/o;
131 13 my $r_STRING_LITERAL_LONG2 = qr/"""(("|"")?([^"\\]|${r_ECHAR}))*"""/o;
132 13 my $r_LANGTAG = qr/@[a-zA-Z]+(-[a-zA-Z0-9]+)*/o;
133 13 my $r_LANGTAG_12 = qr/@[a-zA-Z]+(-[a-zA-Z0-9]+)*(--[a-zA-Z]+)?/o;
134 13 my $r_IRI_REF = qr/<([^<>"{}|^`\\\x{00}-\x{20}])*>/o;
135 13 my $r_PN_CHARS_BASE = qr/([A-Z]|[a-z]|[\x{00C0}-\x{00D6}]|[\x{00D8}-\x{00F6}]|[\x{00F8}-\x{02FF}]|[\x{0370}-\x{037D}]|[\x{037F}-\x{1FFF}]|[\x{200C}-\x{200D}]|[\x{2070}-\x{218F}]|[\x{2C00}-\x{2FEF}]|[\x{3001}-\x{D7FF}]|[\x{F900}-\x{FDCF}]|[\x{FDF0}-\x{FFFD}]|[\x{10000}-\x{EFFFF}])/o;
136 13 my $r_PN_CHARS_U = qr/([_]|${r_PN_CHARS_BASE})/o;
137 13 my $r_VARNAME = qr/((${r_PN_CHARS_U}|[0-9])(${r_PN_CHARS_U}|[0-9]|\x{00B7}|[\x{0300}-\x{036F}]|[\x{203F}-\x{2040}])*)/o;
138 13 my $r_VAR1 = qr/[?]${r_VARNAME}/o;
139 13 my $r_VAR2 = qr/[\$]${r_VARNAME}/o;
140 13 my $r_PN_CHARS = qr/${r_PN_CHARS_U}|-|[0-9]|\x{00B7}|[\x{0300}-\x{036F}]|[\x{203F}-\x{2040}]/o;
141 13 my $r_PN_PREFIX = qr/(${r_PN_CHARS_BASE}((${r_PN_CHARS}|[.])*${r_PN_CHARS})?)/o;
142 13 my $r_PN_LOCAL_ESCAPED = qr{(\\([-~.!&'()*+,;=/?#@%_\$]))|%[0-9A-Fa-f]{2}}o;
143 13 my $r_PN_LOCAL = qr/((${r_PN_CHARS_U}|[:0-9]|${r_PN_LOCAL_ESCAPED})((${r_PN_CHARS}|${r_PN_LOCAL_ESCAPED}|[:.])*(${r_PN_CHARS}|[:]|${r_PN_LOCAL_ESCAPED}))?)/o;
144 13 my $r_PN_LOCAL_BNODE = qr/((${r_PN_CHARS_U}|[0-9])((${r_PN_CHARS}|[.])*${r_PN_CHARS})?)/o;
145 13 my $r_PNAME_NS = qr/((${r_PN_PREFIX})?:)/o;
146 13 my $r_PNAME_LN = qr/(${r_PNAME_NS}${r_PN_LOCAL})/o;
147 13 my $r_EXPONENT = qr/[eE][-+]?\d+/o;
148 13 my $r_DOUBLE = qr/\d+[.]\d*${r_EXPONENT}|[.]\d+${r_EXPONENT}|\d+${r_EXPONENT}/o;
149 13 my $r_DECIMAL = qr/(\d+[.]\d*)|([.]\d+)/o;
150 13 my $r_INTEGER = qr/\d+/o;
151 13 my $r_BLANK_NODE_LABEL = qr/_:${r_PN_LOCAL_BNODE}/o;
152 13 my $r_ANON = qr/\[[\t\r\n ]*\]/o;
153 13 my $r_NIL = qr/\([\n\r\t ]*\)/o;
154 13 my $r_KEYWORDS = qr/(ABS|ADD|ALL|ASC|ASK|AS|AVG|BASE|BIND|BNODE|BOUND|BY|CEIL|CLEAR|COALESCE|CONCAT|CONSTRUCT|CONTAINS|COPY|COUNT|CREATE|DATA|DATATYPE|DAY|DEFAULT|DELETE|DELETE WHERE|DESCRIBE|DESC|DISTINCT|DISTINCT|DROP|ENCODE_FOR_URI|EXISTS|FILTER|FLOOR|FOLD|FROM|GRAPH|GROUP_CONCAT|GROUP|HASLANG|HASLANGDIR|HAVING|HINT|HOURS|IF|IN|INSERT|INTO|IRI|ISBLANK|ISIRI|ISLITERAL|ISNUMERIC|ISURI|LANGDIR|LANGMATCHES|LANG|LCASE|LIMIT|LOAD|MAX|MD5|MINUS|MINUTES|MIN|MONTH|MOVE|NAMED|NOT|NOW|OFFSET|OPTIONAL|ORDER|PREFIX|RAND|REDUCED|REGEX|REPLACE|ROUND|SAMETERM|SAMPLE|SECONDS|SELECT|SEPARATOR|SERVICE|SHA1|SHA256|SHA384|SHA512|SILENT|STR|STRAFTER|STRBEFORE|STRDT|STRENDS|STRLANG|STRLEN|STRSTARTS|STRUUID|SUBSTR|SUM|TIMEZONE|TO|TZ|UCASE|UNDEF|UNFOLD|UNION|URI|USING|UUID|VALUES|WHERE|WITH|YEAR)(?!:)\b/io;
155 13 my $r_KEYWORDS_12 = qr/(VERSION|ABS|ADD|ALL|ASC|ASK|AS|AVG|BASE|BIND|BNODE|BOUND|BY|CEIL|CLEAR|COALESCE|CONCAT|CONSTRUCT|CONTAINS|COPY|COUNT|CREATE|DATA|DATATYPE|DAY|DEFAULT|DELETE|DELETE WHERE|DESCRIBE|DESC|DISTINCT|DISTINCT|DROP|ENCODE_FOR_URI|EXISTS|FILTER|FLOOR|FOLD|FROM|GRAPH|GROUP_CONCAT|GROUP|HASLANG|HASLANGDIR|HAVING|HINT|HOURS|IF|IN|INSERT|INTO|IRI|ISBLANK|ISIRI|ISLITERAL|ISNUMERIC|ISTRIPLE|ISURI|LANGDIR|LANGMATCHES|LANG|LCASE|LIMIT|LOAD|MAX|MD5|MINUS|MINUTES|MIN|MONTH|MOVE|NAMED|NOT|NOW|OBJECT|OFFSET|OPTIONAL|ORDER|PREDICATE|PREFIX|RAND|REDUCED|REGEX|REPLACE|ROUND|SAMETERM|SAMPLE|SECONDS|SELECT|SEPARATOR|SERVICE|SHA1|SHA256|SHA384|SHA512|SILENT|STR|STRAFTER|STRBEFORE|STRDT|STRENDS|STRLANGDIR|STRLANG|STRLEN|STRSTARTS|STRUUID|SUBJECT|SUBSTR|SUM|TIMEZONE|TO|TRIPLE|TZ|UCASE|UNDEF|UNFOLD|UNION|URI|USING|UUID|VALUES|WHERE|WITH|YEAR)(?!:)\b/io;
156  
157 67 ▶ sub BUILD {
Subroutine BUILD: called CC=8 SCAR=21.9
Pod undocumented
158 67 my $self = shift;
159 my %METHOD_TOKEN = (
160 # q[#] => '_get_comment',
161 q[@] => '_get_lang',
162 q[<] => '_get_iriref_or_relational',
163 q[{] => '_get_brace_or_annotation_or_or',
164 q[}] => '_get_brace_or_annotation_or_or',
165 q[|] => '_get_brace_or_annotation_or_or',
166 q[_] => '_get_bnode',
167 q['] => '_get_single_literal',
168 q["] => '_get_double_literal',
169 q[:] => '_get_pname',
170 q[?] => '_get_variable',
171 q[$] => '_get_variable',
172 q[!] => '_get_bang',
173 q[>] => '_get_iriref_or_relational',
174 q([) => '_get_lbracket_or_anon',
175 q[(] => '_get_lparen_or_nil',
176 q[)] => '_get_rparen_or_pgtgt',
177 67 (map {$_ => '_get_number'} (0 .. 9, '-', '+'))
178 );
179 67 ▶ while (my ($k,$v) = each(%METHOD_TOKEN)) {
Branch: 1 branch
BranchTrueFalseTotal
if (() = each %METHOD_TOKEN) 1876 67 1943
180 1876 ▶ if (length($k) != 1) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $k != 1) 0 1876 1876
181 0 die "Cannot set a lookahead token handler method with lookahead > 1 char";
182 }
183 1876 ▶ $self->lookahead_methods->{$k} //= $v;
Condition33%1/3
$self->lookahead_methods->{$k} //= $v
l!l&&r!l&&!r
018760
MC/DC0%0/2
$self->lookahead_methods->{$k} //= $v
$self->lookahead_methods->{$k} $v
Truth table33%1/3
A //= B
A= $self->lookahead_methods->{$k}B= $v
ABresult
1X1
011
000
184 }
185  
186 67 my %CHAR_TOKEN = (
187 ',' => COMMA,
188 '.' => DOT,
189 '=' => EQUALS,
190 ']' => RBRACKET,
191 '-' => MINUS,
192 '+' => PLUS,
193 ';' => SEMICOLON,
194 '/' => SLASH,
195 '*' => STAR,
196 '~' => TILDE,
197 );
198 67 ▶ while (my ($k,$v) = each(%CHAR_TOKEN)) {
Branch: 1 branch
BranchTrueFalseTotal
if (() = each %CHAR_TOKEN) 670 67 737
199 670 ▶ if (length($k) != 1) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $k != 1) 0 670 670
200 0 die "Cannot set a lookahead token with lookahead > 1 char";
201 }
202 670 ▶ $self->lookahead_tokens->{$k} //= $v;
Condition33%1/3
$self->lookahead_tokens->{$k} //= $v
l!l&&r!l&&!r
06700
MC/DC0%0/2
$self->lookahead_tokens->{$k} //= $v
$self->lookahead_tokens->{$k} $v
Truth table33%1/3
A //= B
A= $self->lookahead_tokens->{$k}B= $v
ABresult
1X1
011
000
203 }
204
205 67 ▶ if ($self->version ge '1.2') {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->version ge '1.2') { } 63 4 67
206 63 ▶ $self->add_regex_rule( $r_KEYWORDS_12, KEYWORD, sub { return uc(shift) } );
Subroutine __ANON__: called CC=1 SCAR=0.0
207 } else {
208 4 ▶ $self->add_regex_rule( $r_KEYWORDS, KEYWORD, sub { return uc(shift) } );
Subroutine __ANON__: called CC=1 SCAR=0.0
209 }
210 }
211  
212 349 ▶ sub sparql12 {
Subroutine sparql12: called CC=1 SCAR=0.0
Pod undocumented
213 349 my $self = shift;
214 349 return ($self->version ge '1.2');
215 }
216  
217 5848 ▶ sub peek {
Subroutine peek: called CC=2 SCAR=6.9
Pod undocumented
218 5848 my $self = shift;
219 5848 my $b = $self->token_buffer;
220 5848 my $t = $self->next;
221 5847 ▶ return unless ($t);
Branch: 1 branch
BranchTrueFalseTotal
unless $t 279 5568 5847
222 5568 push(@$b, $t);
223 5568 return $t;
224 }
225
226 6649 ▶ sub next {
Subroutine next: called CC=2 SCAR=6.9
Pod undocumented
227 6649 my $self = shift;
228 6649 my $b = $self->token_buffer;
229 6649 ▶ if (scalar(@$b)) {
Branch: 1 branch
BranchTrueFalseTotal
if (scalar @$b) { } 5567 1082 6649
230 5567 return shift(@$b);
231 } else {
232 1082 return $self->get_token();
233 }
234 }
235
236 4 ▶ sub codepoint_unescape {
Subroutine codepoint_unescape: called CC=3 SCAR=11.4
Pod undocumented
237 4 my $self = shift;
238 4 my $value = shift;
239 13 ▶ no warnings 'uninitialized';
Subroutine BEGIN: called CC=1 SCAR=0.0
240 4 $value =~ s{\\(?:(?:u([0-9A-Fa-f]{4}))|(?:U([0-9A-Fa-f]{8})))}{
241 4 my $h = $1 . $2;
242 4 my $codepoint = hex($h);
243 4 ▶ if ($codepoint >= 0xD800 and $codepoint <= 0xDFFF) {
Branch: 1 branch
BranchTrueFalseTotal
if ($codepoint >= 55296 and $codepoint <= 57343) 0 4 4
Condition33%1/3
$codepoint >= 55296 and $codepoint <= 57343
!ll&&!rl&&r
400
MC/DC0%0/2
$codepoint >= 55296 and $codepoint <= 57343
$codepoint >= 55296 $codepoint <= 57343
Truth table33%1/3
A and B
A= $codepoint >= 55296B= $codepoint <= 57343
ABresult
0X0
100
111
244 0 die "Unicode surrogate U+$h is illegal in UTF-8";
245 }
246 4 chr($codepoint);
247 }ge;
248 4 return $value;
249 }
250
251 662 ▶ sub fill_buffer {
Subroutine fill_buffer: called CC=5 SCAR=16.4
Pod undocumented
252 662 my $self = shift;
253 662 ▶ unless (length($self->buffer)) {
Branch: 1 branch
BranchTrueFalseTotal
unless (length $self->buffer) 662 0 662
254 662 AGAIN:
255 my $line = $self->file->getline;
256 662 ▶ if (defined($line)) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $line) 92 570 662
257 92 ▶ if ($self->version lt '1.2') {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->version lt "1.2") 4 88 92
258 # codepoint escape handling has moved into the literal and IRI handling in SPARQL 1.2+
259 4 $line = $self->codepoint_unescape($line);
260 }
261 92 $self->{buffer} .= $line;
262 92 ▶ if ($line =~ /[[(]\s*$/) { # might be a NIL or ANON that spans a line
Branch: 1 branch
BranchTrueFalseTotal
if ($line =~ /[[(]\s*$/u) 0 92 92
263 0 goto AGAIN;
264 }
265 }
266 }
267 }
268
269 794 ▶ sub new_token {
Subroutine new_token: called CC=1 SCAR=0.0
Pod undocumented
270 794 my $self = shift;
271 794 my $type = shift;
272 794 my $start_line = shift;
273 794 my $start_col = shift;
274 794 my $line = $self->line;
275 794 my $col = $self->column;
276 794 return AtteanX::SPARQL::Token->fast_constructor( $type, $start_line, $start_col, $line, $col, \@_ );
277 }
278  
279 120 ▶ sub add_regex_rule {
Subroutine add_regex_rule: called CC=1 SCAR=0.0
Pod undocumented
280 120 my $self = shift;
281 120 my $r = shift;
282 120 my $ttype = shift;
283 120 my $convert = shift;
284 120 my $extend = $self->extend;
285 1357 ▶ push(@$extend, sub {
Subroutine __ANON__: called CC=3 SCAR=11.0
286 1357 my $l = shift;
287
288 1357 ▶ if ($l->buffer =~ /^$r\b/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($l->buffer =~ /^$r\b/u) 183 1174 1357
289 183 my $value = $self->read_length($+[0]);
290 183 ▶ my $c = $convert ? $convert->($value) : $value;
Branch: 1 branch
BranchTrueFalseTotal
$convert ? : 183 0 183
291 183 return $l->new_token($ttype, $l->start_line, $l->start_column, $c);
292 }
293 120 });
294 }
295
296 1082 ▶ sub get_token {
Subroutine get_token: called CC=19 SCAR=33.3
Pod undocumented
297 1082 my $self = shift;
298 1082 while (1) {
299 1756 ▶ $self->fill_buffer unless (length($self->buffer));
Branch: 1 branch
BranchTrueFalseTotal
unless length $self->buffer 377 1379 1756
300  
301 1756 ▶ if ($self->buffer =~ /^[ \r\n\t]+/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^[ \r\n\t]+/ou) 674 1082 1756
302 674 $self->read_length($+[0]);
303 # we're ignoring whitespace tokens, but we could return them here instead of falling through to the 'next':
304 # return $self->new_token(WS);
305 674 next;
306 }
307  
308 1082 my $c = $self->peek_char();
309 1082 ▶ return unless (defined($c));
Branch: 1 branch
BranchTrueFalseTotal
unless defined $c 285 797 1082
310  
311 797 ▶ if ($c eq '#') {
Branch: 1 branch
BranchTrueFalseTotal
if ($c eq "#") 0 797 797
312 # we're ignoring comment tokens, but we could return them here instead of falling through to the 'next':
313 0 $self->_get_comment();
314 0 next;
315 }
316
317 797 my $start_column = $self->column;
318 797 my $start_line = $self->line;
319
320 797 $self->start_column( $start_column );
321 797 $self->start_line( $start_line );
322
323 797 foreach my $e (@{ $self->extend }) {
324 1357 ▶ if (my $t = $e->( $self )) {
Branch: 1 branch
BranchTrueFalseTotal
if (my $t = &$e($self)) 183 1174 1357
325 183 return $t;
326 }
327 }
328
329 614 ▶ if ($c eq '.' and $self->buffer =~ /^$r_DECIMAL/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($c eq "." and $self->buffer =~ /^$r_DECIMAL/u) 0 614 614
Condition66%2/3
$c eq "." and $self->buffer =~ /^$r_DECIMAL/u
!ll&&!rl&&r
60590
MC/DC0%0/2
$c eq "." and $self->buffer =~ /^$r_DECIMAL/u
$c eq "." $self->buffer =~ /^$r_DECIMAL/u
Truth table66%2/3
A and B
A= $c eq "."B= $self->buffer =~ /^$r_DECIMAL/u
ABresult
0X0
100
111
330 0 return $self->_get_number();
331 }
332
333 614 ▶ if (defined(my $name = $self->lookahead_tokens->{$c})) { $self->get_char; return $self->new_token($name, $start_line, $start_column, $c); }
Branch: 5 branches
BranchTrueFalseTotal
if (defined(my $name = $self->lookahead_tokens->{$c})) { } 66 548 614
elsif (defined(my $method = $self->lookahead_methods->{$c})) { } 486 62 548
elsif ($c =~ /[A-Za-z\x{00C0}-\x{00D6}\x{00D8}-\x{00F6}\x{00F8}-\x{02FF}\x{0370}-\x{037D}\x{037F}-\x{1FFF}\x{200C}-\x{200D}\x{2070}-\x{218F}\x{2C00}-\x{2FEF}\x{3001}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFFD}\x{10000}-\x{EFFFF}]/ou) { } 61 1 62
elsif ($c eq '^') { } 0 1 1
elsif ($c eq '&') { } 1 0 1
334 486 elsif (defined(my $method = $self->lookahead_methods->{$c})) { return $self->$method() }
335 elsif ($c =~ /[A-Za-z\x{00C0}-\x{00D6}\x{00D8}-\x{00F6}\x{00F8}-\x{02FF}\x{0370}-\x{037D}\x{037F}-\x{1FFF}\x{200C}-\x{200D}\x{2070}-\x{218F}\x{2C00}-\x{2FEF}\x{3001}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFFD}\x{10000}-\x{EFFFF}]/o) {
336 61 ▶ if ($self->buffer =~ /^a(?!:)\s/o) {
Branch: 4 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^a(?!:)\s/ou) { } 13 48 61
elsif ($self->buffer =~ /^(?i:true|false)(?!:)\b/ou) { } 6 42 48
elsif ($self->buffer =~ /^BASE(?!:)\b/iou) { } 0 42 42
elsif ($self->buffer =~ /^PREFIX(?!:)\b/iou) { } 0 42 42
337 13 $self->get_char;
338 13 return $self->new_token(A, $start_line, $start_column, 'a');
339 } elsif ($self->buffer =~ /^(?i:true|false)(?!:)\b/o) {
340 6 my $bool = $self->read_length($+[0]);
341 6 return $self->new_token(BOOLEAN, $start_line, $start_column, lc($bool));
342 # } elsif ($self->buffer =~ /^$r_KEYWORDS/) {
343 # my $bool = $self->read_length($+[0]);
344 # return $self->new_token(KEYWORD, $start_line, $start_column, $bool);
345 } elsif ($self->buffer =~ /^BASE(?!:)\b/oi) {
346 0 $self->read_length(4);
347 0 return $self->new_token(BASE, $start_line, $start_column, 'BASE');
348 } elsif ($self->buffer =~ /^PREFIX(?!:)\b/io) {
349 0 $self->read_length(6);
350 0 return $self->new_token(PREFIX, $start_line, $start_column, 'PREFIX');
351 } else {
352 42 return $self->_get_pname;
353 }
354 } elsif ($c eq '^') {
355 0 ▶ if ($self->buffer =~ /^\^\^/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^\^\^/u) { } 0 0 0
356 0 $self->read_word('^^');
357 0 return $self->new_token(HATHAT, $start_line, $start_column, '^^');
358 } else {
359 0 $self->read_word('^');
360 0 return $self->new_token(HAT, $start_line, $start_column, '^');
361 }
362 } elsif ($c eq '&') {
363 1 $self->read_word('&&');
364 1 return $self->new_token(ANDAND, $start_line, $start_column, '&&');
365 } else {
366 # Carp::cluck sprintf("Unexpected byte '$c' (0x%02x)", ord($c));
367 0 return $self->_throw_error(sprintf("Unexpected byte '%s' (0x%02x)", $c, ord($c)));
368 }
369 0 warn sprintf('byte: 0x%x', ord($c));
370 }
371 }
372  
373 53 ▶ sub _get_pname {
Subroutine _get_pname: called CC=3 SCAR=11.0
374 53 my $self = shift;
375 53 my $prefix = '';
376
377 53 ▶ if ($self->buffer =~ /^$r_PNAME_LN/o) {
Branch: 2 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_PNAME_LN/ou) { } 35 18 53
elsif ($self->buffer =~ /$r_PNAME_NS/u) { } 16 2 18
378 35 my $ln = $self->read_length($+[0]);
379 35 my ($ns, $local) = ($ln =~ /^([^:]*:)(.*)$/);
380 13 ▶ no warnings 'uninitialized';
Subroutine BEGIN: called CC=1 SCAR=0.0
381 35 $local =~ s{\\([-~.!&'()*+,;=:/?#@%_\$])}{$1}g;
382 35 return $self->new_token(PREFIXNAME, $self->start_line, $self->start_column, $ns, $local);
383 } elsif ($self->buffer =~ $r_PNAME_NS) {
384 16 my $ns = $self->read_length($+[0]);
385 16 return $self->new_token(PREFIXNAME, $self->start_line, $self->start_column, $ns);
386 } else {
387 2 $self->_throw_error("Expected PNAME");
388 }
389 }
390  
391 144 ▶ sub _get_variable {
Subroutine _get_variable: called CC=4 SCAR=19.1
392 144 my $self = shift;
393 144 ▶ if (substr($self->buffer, 0, 1) eq '$') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '$') { } 0 144 144
394 0 $self->get_char_safe('$');
395 0 ▶ if ($self->buffer =~ /^$r_VARNAME/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_VARNAME/u) { } 0 0 0
396 0 my $name = $self->read_length($+[0]);
397 0 return $self->new_token(VAR, $self->start_line, $self->start_column, $name);
398 } else {
399 0 $self->_throw_error("Invalid variable name");
400 }
401 } else {
402 144 $self->get_char_safe('?');
403 144 ▶ if ($self->buffer =~ /^$r_VARNAME/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_VARNAME/u) { } 144 0 144
404 144 my $name = $self->read_length($+[0]);
405 144 return $self->new_token(VAR, $self->start_line, $self->start_column, $name);
406 } else {
407 0 return $self->new_token(QUESTION, $self->start_line, $self->start_column, '?');
408 }
409 }
410 }
411
412 99 ▶ sub _get_iriref_or_relational {
Subroutine _get_iriref_or_relational: called CC=24 SCAR=50.5
413 99 my $self = shift;
414 99 my $buffer = $self->buffer;
415 99 ▶ if ($buffer =~ m/^<([^<>"{}|^`\x00-\x20])*>/) {
Branch: 8 branches
BranchTrueFalseTotal
if ($buffer =~ /^<([^<>"{}|^`\x00-\x20])*>/u) { } 87 12 99
elsif (substr($buffer, 0, 2) eq '<=') { } 0 12 12
elsif (substr($buffer, 0, 2) eq '>=') { } 0 12 12
elsif ($self->sparql12 and substr($buffer, 0, 3) eq '<<(') { } 1 11 12
elsif ($self->sparql12 and substr($buffer, 0, 2) eq '<<') { } 4 7 11
elsif ($self->sparql12 and substr($buffer, 0, 2) eq '>>') { } 4 3 7
elsif (substr($buffer, 0, 1) eq '>') { } 1 2 3
elsif (substr($buffer, 0, 1) eq '<') { } 2 0 2
416 87 $self->get_char_safe(q[<]);
417 87 ▶ if ($self->buffer =~ m/^[\x23-\x3d\x3f-\x5a\x5d-\x7e]*>/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^[\x23-\x3d\x3f-\x5a\x5d-\x7e]*>/ou) 87 0 87
418 87 my $iri .= $self->read_length($+[0]);
419 87 chop($iri);
420 87 return $self->new_token(IRI, $self->start_line, $self->start_column, $iri);
421 }
422
423 0 my $iri = '';
424 0 while (1) {
425 0 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 0 0
426 0 my $c = $self->peek_char;
427 0 ▶ last unless defined($c);
Branch: 1 branch
BranchTrueFalseTotal
unless defined $c 0 0 0
428 }
429 0 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 0 0 0
elsif ($self->buffer =~ /^[^<>\x00-\x20\\"{}|^`]+/ou) { } 0 0 0
elsif (substr($self->buffer, 0, 1) eq '>') { } 0 0 0
430 0 $self->get_char_safe('\\');
431 0 my $esc = $self->get_char;
432 0 ▶ if ($esc eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if ($esc eq '\\') { } 0 0 0
elsif ($esc eq 'U') { } 0 0 0
elsif ($esc eq 'u') { } 0 0 0
433 0 $iri .= "\\";
434 } elsif ($esc eq 'U') {
435 0 my $codepoint = $self->read_length(8);
436 0 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($codepoint =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $codepoint =~ /^[0-9A-Fa-f]+$/ou 0 0 0
437 0 $iri .= chr(hex($codepoint));
438 } elsif ($esc eq 'u') {
439 0 my $codepoint = $self->read_length(4);
440 0 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($codepoint =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $codepoint =~ /^[0-9A-Fa-f]+$/ou 0 0 0
441 0 my $char = chr(hex($codepoint));
442 0 ▶ if ($char =~ /[<>" {}|\\^`]/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($char =~ /[<>" {}|\\^`]/ou) 0 0 0
443 0 $self->_throw_error(sprintf("Bad IRI character: '%s' (0x%x)", $char, ord($char)));
444 }
445 0 $iri .= $char;
446 } else {
447 0 $self->_throw_error("Unrecognized iri escape '$esc'");
448 }
449 } elsif ($self->buffer =~ /^[^<>\x00-\x20\\"{}|^`]+/o) {
450 0 $iri .= $self->read_length($+[0]);
451 } elsif (substr($self->buffer, 0, 1) eq '>') {
452 0 last;
453 } else {
454 0 my $c = $self->peek_char;
455 0 $self->_throw_error("Got '$c' while expecting IRI character");
456 }
457 }
458 0 $self->get_char_safe(q[>]);
459 0 return $self->new_token(IRI, $self->start_line, $self->start_column, $iri);
460 } elsif (substr($buffer, 0, 2) eq '<=') {
461 0 $self->read_length(2);
462 0 return $self->new_token(LE, $self->start_line, $self->start_column, '<=');
463 } elsif (substr($buffer, 0, 2) eq '>=') {
464 0 $self->read_length(2);
465 0 return $self->new_token(GE, $self->start_line, $self->start_column, '>=');
466 ▶ } elsif ($self->sparql12 and substr($buffer, 0, 3) eq '<<(') {
Condition66%2/3
$self->sparql12 and substr($buffer, 0, 3) eq "<<("
!ll&&!rl&&r
0111
MC/DC50%1/2
$self->sparql12 and substr($buffer, 0, 3) eq "<<("
$self->sparql12 substr($buffer, 0, 3) eq "<<("
Truth table66%2/3
A and B
A= $self->sparql12B= substr($buffer, 0, 3) eq "<<("
ABresult
0X0
100
111
467 1 $self->read_length(3);
468 1 return $self->new_token(LTLTP, $self->start_line, $self->start_column, '<<(');
469 ▶ } elsif ($self->sparql12 and substr($buffer, 0, 2) eq '<<') {
Condition66%2/3
$self->sparql12 and substr($buffer, 0, 2) eq "<<"
!ll&&!rl&&r
074
MC/DC50%1/2
$self->sparql12 and substr($buffer, 0, 2) eq "<<"
$self->sparql12 substr($buffer, 0, 2) eq "<<"
Truth table66%2/3
A and B
A= $self->sparql12B= substr($buffer, 0, 2) eq "<<"
ABresult
0X0
100
111
470 4 $self->read_length(2);
471 4 return $self->new_token(LTLT, $self->start_line, $self->start_column, '<<');
472 ▶ } elsif ($self->sparql12 and substr($buffer, 0, 2) eq '>>') {
Condition66%2/3
$self->sparql12 and substr($buffer, 0, 2) eq ">>"
!ll&&!rl&&r
034
MC/DC50%1/2
$self->sparql12 and substr($buffer, 0, 2) eq ">>"
$self->sparql12 substr($buffer, 0, 2) eq ">>"
Truth table66%2/3
A and B
A= $self->sparql12B= substr($buffer, 0, 2) eq ">>"
ABresult
0X0
100
111
473 4 $self->read_length(2);
474 4 return $self->new_token(GTGT, $self->start_line, $self->start_column, '>>');
475 } elsif (substr($buffer, 0, 1) eq '>') {
476 1 $self->get_char;
477 1 return $self->new_token(GT, $self->start_line, $self->start_column, '>');
478 } elsif (substr($buffer, 0, 1) eq '<') {
479 2 $self->get_char;
480 2 return $self->new_token(LT, $self->start_line, $self->start_column, '<');
481 } else {
482 0 die "Unrecognized relational op near '$buffer'";
483 }
484 }
485  
486 1 ▶ sub _get_bang {
Subroutine _get_bang: called CC=2 SCAR=7.9
487 1 my $self = shift;
488 1 ▶ if ($self->buffer =~ /^!=/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^!=/u) { } 0 1 1
489 0 $self->read_length(2);
490 0 return $self->new_token(NOTEQUALS, $self->start_line, $self->start_column, '!=');
491 } else {
492 1 $self->get_char;
493 1 return $self->new_token(BANG, $self->start_line, $self->start_column, '!');
494 }
495 }
496
497 0 ▶ sub _get_bnode {
Subroutine _get_bnode: not called CC=2 SCAR=17.9
498 0 my $self = shift;
499 0 ▶ unless ($self->buffer =~ /^$r_BLANK_NODE_LABEL/o) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($self->buffer =~ /^$r_BLANK_NODE_LABEL/ou) 0 0 0
500 0 $self->_throw_error("Expected: name");
501 }
502 0 my $ln = $self->read_length($+[0]);
503 0 my $name = substr($ln, 2);
504 0 return $self->new_token(BNODE, $self->start_line, $self->start_column, $name);
505 }
506  
507 18 ▶ sub _get_number {
Subroutine _get_number: called CC=4 SCAR=14.0
508 18 my $self = shift;
509 18 ▶ if ($self->buffer =~ /^${r_DOUBLE}/o) {
Branch: 3 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_DOUBLE/ou) { } 1 17 18
elsif ($self->buffer =~ /^$r_DECIMAL/ou) { } 1 16 17
elsif ($self->buffer =~ /^$r_INTEGER/ou) { } 16 0 16
510 1 return $self->new_token(DOUBLE, $self->start_line, $self->start_column, $self->read_length($+[0]));
511 } elsif ($self->buffer =~ /^${r_DECIMAL}/o) {
512 1 return $self->new_token(DECIMAL, $self->start_line, $self->start_column, $self->read_length($+[0]));
513 } elsif ($self->buffer =~ /^${r_INTEGER}/o) {
514 16 return $self->new_token(INTEGER, $self->start_line, $self->start_column, $self->read_length($+[0]));
515 }
516 0 $self->_throw_error("Expected number");
517 }
518  
519 20 ▶ sub _get_lparen_or_nil {
Subroutine _get_lparen_or_nil: called CC=2 SCAR=6.9
520 20 my $self = shift;
521 20 ▶ if ($self->buffer =~ /^$r_NIL/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_NIL/u) { } 1 19 20
522 1 $self->read_length($+[0]);
523 1 return $self->new_token(NIL, $self->start_line, $self->start_column, '()');
524 } else {
525 19 $self->get_char_safe('(');
526 19 return $self->new_token(LPAREN, $self->start_line, $self->start_column, '(');
527 }
528 }
529
530 19 ▶ sub _get_rparen_or_pgtgt {
Subroutine _get_rparen_or_pgtgt: called CC=3 SCAR=11.0
531 19 my $self = shift;
532 19 ▶ if ($self->sparql12 and substr($self->buffer, 0, 3) eq ')>>') {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->sparql12 and substr($self->buffer, 0, 3) eq ')>>') { } 1 18 19
Condition66%2/3
$self->sparql12 and substr($self->buffer, 0, 3) eq ")>>"
!ll&&!rl&&r
0181
MC/DC50%1/2
$self->sparql12 and substr($self->buffer, 0, 3) eq ")>>"
$self->sparql12 substr($self->buffer, 0, 3) eq ")>>"
Truth table66%2/3
A and B
A= $self->sparql12B= substr($self->buffer, 0, 3) eq ")>>"
ABresult
0X0
100
111
533 1 $self->read_length(3);
534 1 return $self->new_token(PGTGT, $self->start_line, $self->start_column, ')>>');
535 } else {
536 18 $self->get_char_safe(')');
537 18 return $self->new_token(RPAREN, $self->start_line, $self->start_column, ')');
538 }
539 }
540
541 148 ▶ sub _get_brace_or_annotation_or_or {
Subroutine _get_brace_or_annotation_or_or: called CC=8 SCAR=21.4
542 148 my $self = shift;
543 148 ▶ if ($self->sparql12 and substr($self->buffer, 0, 2) eq '{|') {
Branch: 5 branches
BranchTrueFalseTotal
if ($self->sparql12 and substr($self->buffer, 0, 2) eq '{|') { } 2 146 148
elsif ($self->sparql12 and substr($self->buffer, 0, 2) eq '|}') { } 2 144 146
elsif (substr($self->buffer, 0, 2) eq '||') { } 0 144 144
elsif (substr($self->buffer, 0, 1) eq '{') { } 73 71 144
elsif (substr($self->buffer, 0, 1) eq '}') { } 71 0 71
Condition100%3/3
$self->sparql12 and substr($self->buffer, 0, 2) eq "{|"
!ll&&!rl&&r
41422
MC/DC100%2/2
$self->sparql12 and substr($self->buffer, 0, 2) eq "{|"
$self->sparql12 substr($self->buffer, 0, 2) eq "{|"
Truth table100%3/3
A and B
A= $self->sparql12B= substr($self->buffer, 0, 2) eq "{|"
ABresult
0X0
100
111
544 2 $self->read_length(2);
545 2 return $self->new_token(LANNOT, $self->start_line, $self->start_column, '{|');
546 ▶ } elsif ($self->sparql12 and substr($self->buffer, 0, 2) eq '|}') {
Condition100%3/3
$self->sparql12 and substr($self->buffer, 0, 2) eq "|}"
!ll&&!rl&&r
41402
MC/DC100%2/2
$self->sparql12 and substr($self->buffer, 0, 2) eq "|}"
$self->sparql12 substr($self->buffer, 0, 2) eq "|}"
Truth table100%3/3
A and B
A= $self->sparql12B= substr($self->buffer, 0, 2) eq "|}"
ABresult
0X0
100
111
547 2 $self->read_length(2);
548 2 return $self->new_token(RANNOT, $self->start_line, $self->start_column, '|}');
549 } elsif (substr($self->buffer, 0, 2) eq '||') {
550 0 $self->read_length(2);
551 0 return $self->new_token(OROR, $self->start_line, $self->start_column, '||');
552 } elsif (substr($self->buffer, 0, 1) eq '{') {
553 73 $self->get_char_safe('{');
554 73 return $self->new_token(LBRACE, $self->start_line, $self->start_column, '{');
555 } elsif (substr($self->buffer, 0, 1) eq '}') {
556 71 $self->get_char_safe('}');
557 71 return $self->new_token(RBRACE, $self->start_line, $self->start_column, '}');
558 } else {
559 0 $self->get_char_safe('|');
560 0 return $self->new_token(OR, $self->start_line, $self->start_column, '|');
561 }
562 }
563  
564 0 ▶ sub _get_lbracket_or_anon {
Subroutine _get_lbracket_or_anon: not called CC=2 SCAR=17.9
565 0 my $self = shift;
566 0 ▶ if ($self->buffer =~ /^$r_ANON/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_ANON/u) { } 0 0 0
567 0 $self->read_length($+[0]);
568 0 return $self->new_token(ANON, $self->start_line, $self->start_column, '[]');
569 } else {
570 0 $self->get_char_safe('[');
571 0 return $self->new_token(LBRACKET, $self->start_line, $self->start_column, '[');
572 }
573 }
574
575 0 ▶ sub _get_comment {
Subroutine _get_comment: not called CC=5 SCAR=34.0
576 0 my $self = shift;
577 0 $self->get_char_safe('#');
578 0 my $comment = '';
579 0 my $c = $self->peek_char;
580 0 ▶ while (length($c) and $c !~ /[\r\n]/o) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $c and not $c =~ /[\r\n]/ou) 0 0 0
Condition0%0/3
length $c and not $c =~ /[\r\n]/ou
!ll&&!rl&&r
000
MC/DC0%0/2
length $c and not $c =~ /[\r\n]/ou
length $c not $c =~ /[\r\n]/ou
Truth table0%0/3
A and not(B)
A= length $cB= not $c =~ /[\r\n]/ou
ABresult
0X0
100
111
581 0 $comment .= $self->get_char;
582 0 $c = $self->peek_char;
583 }
584 0 ▶ if (length($c) and $c =~ /[\r\n]/o) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $c and $c =~ /[\r\n]/ou) 0 0 0
Condition0%0/3
length $c and $c =~ /[\r\n]/ou
!ll&&!rl&&r
000
MC/DC0%0/2
length $c and $c =~ /[\r\n]/ou
length $c $c =~ /[\r\n]/ou
Truth table0%0/3
A and B
A= length $cB= $c =~ /[\r\n]/ou
ABresult
0X0
100
111
585 0 $self->get_char;
586 }
587 0 return $self->new_token(COMMENT, $self->start_line, $self->start_column, $comment);
588 }
589  
590 2 ▶ sub _get_lang {
Subroutine _get_lang: called CC=3 SCAR=11.6
591 2 my $self = shift;
592 2 ▶ my $lang_re = ($self->version ge '1.2') ? $r_LANGTAG_12 : $r_LANGTAG;
Branch: 1 branch
BranchTrueFalseTotal
$self->version ge '1.2' ? : 2 0 2
593 2 ▶ if ($self->buffer =~ $lang_re) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /$lang_re/u) 2 0 2
594 2 my $lang = $self->read_length($+[0]);
595 2 substr($lang, 0, 1, ''); # remove the '@' prefix
596 2 return $self->new_token(LANG, $self->start_line, $self->start_column, $lang);
597 }
598 0 $self->_throw_error("Expected keyword or language tag");
599 }
600
601 16 ▶ sub _get_double_literal {
Subroutine _get_double_literal: called CC=12 SCAR=26.6
602 16 my $self = shift;
603 # my $c = $self->peek_char();
604 16 $self->get_char_safe(q["]);
605 16 ▶ if (substr($self->buffer, 0, 2) eq q[""]) {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 2) eq '""') { } 4 12 16
606 # #x22 #x22 #x22 lcharacter* #x22 #x22 #x22
607 4 $self->read_word(q[""]);
608
609 4 my $quote_count = 0;
610 4 my $string = '';
611 4 while (1) {
612 16 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 16 16
613 0 $self->fill_buffer;
614 0 ▶ $self->_throw_error("Found EOF in string literal") if (length($self->buffer) == 0);
Branch: 1 branch
BranchTrueFalseTotal
if length $self->buffer == 0 0 0 0
615 }
616 16 ▶ if (substr($self->buffer, 0, 1) eq '"') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '"') { } 12 4 16
617 12 my $c = $self->get_char;
618 12 $quote_count++;
619 12 ▶ last if ($quote_count == 3);
Branch: 1 branch
BranchTrueFalseTotal
if $quote_count == 3 4 8 12
620 } else {
621 4 ▶ if ($quote_count) {
Branch: 1 branch
BranchTrueFalseTotal
if ($quote_count) 0 4 4
622 0 $string .= '"' foreach (1..$quote_count);
623 0 $quote_count = 0;
624 }
625 4 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 0 4 4
626 0 $string .= $self->read_backslash_escape();
627 } else {
628 4 $self->{buffer} =~ /^[^"\\]+/;
629 4 $string .= $self->read_length($+[0]);
630 }
631 }
632 }
633 4 return $self->new_token(STRING3D, $self->start_line, $self->start_column, $string);
634 } else {
635 ### #x22 scharacter* #x22
636 12 my $string = '';
637 12 while (1) {
638 26 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 5 21 26
elsif ($self->buffer =~ /^[^"\\]+/ou) { } 10 11 21
elsif (substr($self->buffer, 0, 1) eq '"') { } 11 0 11
639 5 $string .= $self->read_backslash_escape();
640 } elsif ($self->buffer =~ /^[^"\\]+/o) {
641 10 $string .= $self->read_length($+[0]);
642 } elsif (substr($self->buffer, 0, 1) eq '"') {
643 11 last;
644 } else {
645 0 my $c = $self->peek_char;
646 0 $self->_throw_error("Got '$c' while expecting string character");
647 }
648 }
649 11 $self->get_char_safe(q["]);
650 11 return $self->new_token(STRING1D, $self->start_line, $self->start_column, $string);
651 }
652 }
653  
654 8 ▶ sub _get_single_literal {
Subroutine _get_single_literal: called CC=12 SCAR=26.6
655 8 my $self = shift;
656 8 $self->get_char_safe("'");
657 8 ▶ if (substr($self->buffer, 0, 2) eq q['']) {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 2) eq q['']) { } 5 3 8
658 # #x22 #x22 #x22 lcharacter* #x22 #x22 #x22
659 5 $self->read_word(q['']);
660
661 5 my $quote_count = 0;
662 5 my $string = '';
663 5 while (1) {
664 20 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 20 20
665 0 $self->fill_buffer;
666 0 ▶ $self->_throw_error("Found EOF in string literal") if (length($self->buffer) == 0);
Branch: 1 branch
BranchTrueFalseTotal
if length $self->buffer == 0 0 0 0
667 }
668 20 ▶ if (substr($self->buffer, 0, 1) eq "'") {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq q[']) { } 15 5 20
669 15 my $c = $self->get_char;
670 15 $quote_count++;
671 15 ▶ last if ($quote_count == 3);
Branch: 1 branch
BranchTrueFalseTotal
if $quote_count == 3 5 10 15
672 } else {
673 5 ▶ if ($quote_count) {
Branch: 1 branch
BranchTrueFalseTotal
if ($quote_count) 0 5 5
674 0 $string .= "'" foreach (1..$quote_count);
675 0 $quote_count = 0;
676 }
677 5 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 0 5 5
678 0 $string .= $self->read_backslash_escape();
679 } else {
680 5 $self->{buffer} =~ /^[^'\\]+/;
681 5 $string .= $self->read_length($+[0]);
682 }
683 }
684 }
685 5 return $self->new_token(STRING3S, $self->start_line, $self->start_column, $string);
686 } else {
687 ### #x22 scharacter* #x22
688 3 my $string = '';
689 3 while (1) {
690 6 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 1 5 6
elsif ($self->buffer =~ /^[^'\\]+/ou) { } 2 3 5
elsif (substr($self->buffer, 0, 1) eq q[']) { } 3 0 3
691 1 $string .= $self->read_backslash_escape();
692 } elsif ($self->buffer =~ /^[^'\\]+/o) {
693 2 $string .= $self->read_length($+[0]);
694 } elsif (substr($self->buffer, 0, 1) eq "'") {
695 3 last;
696 } else {
697 0 my $c = $self->peek_char();
698 0 $self->_throw_error("Got '$c' while expecting string character");
699 }
700 }
701 3 $self->get_char_safe(q[']);
702 3 return $self->new_token(STRING1S, $self->start_line, $self->start_column, $string);
703 }
704 }
705  
706 6 ▶ sub read_backslash_escape {
Subroutine read_backslash_escape: called CC=2 SCAR=6.9
Pod undocumented
707 6 my $self = shift;
708 6 ▶ if ($self->sparql12) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->sparql12) { } 2 4 6
709 # In SPARQL 1.2 all escape logic happens here, including multi-character
710 # escape sequences such as \uXXXX and \UXXXXXXXX.
711 2 return $self->_get_escaped_char(1);
712 } else {
713 # In SPARQL 1.1, multi-character codepoint escape sequences \uXXXX and \UXXXXXXXX
714 # are handled before parsing begins. What is left should only be single-character
715 # escapes such as \t and \n.
716 4 return $self->_get_escaped_char(0);
717 }
718 }
719  
720 6 ▶ sub _get_escaped_char {
Subroutine _get_escaped_char: called CC=17 SCAR=38.7
721 6 my $self = shift;
722 6 my $allow_mb = shift; # allow multi-byte escape sequences such as \uXXXX
723 6 my $c = $self->peek_char;
724 6 $self->get_char_safe('\\');
725 6 my $esc = $self->get_char;
726 0 ▶ if ($esc eq '\\') { return "\\" }
Branch: 8 branches
BranchTrueFalseTotal
if ($esc eq '\\') { } 0 6 6
elsif ($esc =~ /^['">]$/u) { } 3 3 6
elsif ($esc eq 'r') { } 0 3 3
elsif ($esc eq 't') { } 1 2 3
elsif ($esc eq 'n') { } 0 2 2
elsif ($esc eq 'b') { } 0 2 2
elsif ($esc eq 'f') { } 0 2 2
elsif ($allow_mb) { } 2 0 2
727 3 elsif ($esc =~ /^['">]$/) { return $esc }
728 0 elsif ($esc eq 'r') { return "\r" }
729 1 elsif ($esc eq 't') { return "\t" }
730 0 elsif ($esc eq 'n') { return "\n" }
731 0 elsif ($esc eq 'b') { return "\b" }
732 0 elsif ($esc eq 'f') { return "\f" }
733 elsif ($allow_mb) {
734 2 ▶ if ($esc eq 'U') {
Branch: 2 branches
BranchTrueFalseTotal
if ($esc eq 'U') { } 0 2 2
elsif ($esc eq 'u') { } 2 0 2
735 0 my $h = $self->read_length(8);
736 0 my $codepoint = hex($h);
737 0 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($h =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $h =~ /^[0-9A-Fa-f]+$/ou 0 0 0
738 0 ▶ if ($codepoint >= 0xD800 and $codepoint <= 0xDFFF) {
Branch: 1 branch
BranchTrueFalseTotal
if ($codepoint >= 55296 and $codepoint <= 57343) 0 0 0
Condition0%0/3
$codepoint >= 55296 and $codepoint <= 57343
!ll&&!rl&&r
000
MC/DC0%0/2
$codepoint >= 55296 and $codepoint <= 57343
$codepoint >= 55296 $codepoint <= 57343
Truth table0%0/3
A and B
A= $codepoint >= 55296B= $codepoint <= 57343
ABresult
0X0
100
111
739 0 die "Surrogate U+$h is illegal as a codepoint escape value";
740 }
741 0 return chr($codepoint);
742 } elsif ($esc eq 'u'){
743 2 my $h = $self->read_length(4);
744 2 my $codepoint = hex($h);
745 2 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($h =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $h =~ /^[0-9A-Fa-f]+$/ou 0 2 2
746 2 ▶ if ($codepoint >= 0xD800 and $codepoint <= 0xDFFF) {
Branch: 1 branch
BranchTrueFalseTotal
if ($codepoint >= 55296 and $codepoint <= 57343) 1 1 2
Condition66%2/3
$codepoint >= 55296 and $codepoint <= 57343
!ll&&!rl&&r
101
MC/DC50%1/2
$codepoint >= 55296 and $codepoint <= 57343
$codepoint >= 55296 $codepoint <= 57343
Truth table66%2/3
A and B
A= $codepoint >= 55296B= $codepoint <= 57343
ABresult
0X0
100
111
747 1 die "Surrogate U+$h is illegal as a codepoint escape value";
748 }
749 1 return chr($codepoint);
750 }
751 }
752 0 $self->_throw_error("Unrecognized string escape '$esc'");
753 }
754
755 0 ▶ sub current_location {
Subroutine current_location: not called CC=1 SCAR=6.9
Pod undocumented
756 0 my $self = shift;
757 0 return ($self->line, $self->column, $self->buffer);
758 }
759
760 0 ▶ sub throw_near_error {
Subroutine throw_near_error: not called CC=4 SCAR=30.0
Pod undocumented
761 0 my $self = shift;
762 0 my $message = shift;
763 0 ▶ my $line = shift // $self->line;
Condition0%0/3
shift() // $self->line
l!l&&r!l&&!r
000
MC/DC0%0/2
shift() // $self->line
shift() $self->line
Truth table0%0/3
A // B
A= shift()B= $self->line
ABresult
1X1
011
000
764 0 ▶ my $col = shift // $self->column;
Condition0%0/3
shift() // $self->column
l!l&&r!l&&!r
000
MC/DC0%0/2
shift() // $self->column
shift() $self->column
Truth table0%0/3
A // B
A= shift()B= $self->column
ABresult
1X1
011
000
765 0 ▶ my $buffer = shift // $self->buffer;
Condition0%0/3
shift() // $self->buffer
l!l&&r!l&&!r
000
MC/DC0%0/2
shift() // $self->buffer
shift() $self->buffer
Truth table0%0/3
A // B
A= shift()B= $self->buffer
ABresult
1X1
011
000
766 0 die "$message near $line:$col: " . $buffer;
767 }
768
769 2 ▶ sub _throw_error {
Subroutine _throw_error: called CC=1 SCAR=0.0
770 2 my $self = shift;
771 2 my $error = shift;
772 2 my $line = $self->line;
773 2 my $col = $self->column;
774 13 ▶ use Data::Dumper;
Subroutine BEGIN: called CC=1 SCAR=0.0
775 2 Carp::confess "$error at $line:$col with buffer: " . Dumper($self->buffer);
776 }
777 }
778  
779 13 1;
780  
781 __END__
« AtteanX/Serializer/TurtleTokens.pm ↑ Summary AtteanX/Parser/SPARQLXML/SAXHandler.pm »