AtteanX/Parser/Turtle/Lexer.pm

filter: Statementstmt 64.7% 204 / 315 Branchbran 51.2% 85 / 166 Conditioncond 45.0% 9 / 20 MC/DCmcdc 23.0% 3 / 13 Subroutinesub 84.6% 22 / 26 Podpod 66.6% 2 / 3 totaltotal 59.8% 325 / 543 CC 93 SCAR 35.6
CC
93
Cov
59%
_get_iriref_or_ltlt
152.4
get_token
38.9
_get_comment
30.0
CRAP 35.2
« AtteanX/Parser/NTuples.pm ↑ Summary AtteanX/Serializer/TurtleTokens.pm »
1 # AtteanX::Parser::Turtle::Lexer
2 # -----------------------------------------------------------------------------
3  
4 =head1 NAME
5  
6 AtteanX::Parser::Turtle::Lexer - Tokenizer for parsing Turtle, TriG, and N-Triples
7  
8 =head1 VERSION
9  
10 This document describes AtteanX::Parser::Turtle::Lexer version 0.040
11  
12 =head1 SYNOPSIS
13  
14 use AtteanX::Parser::Turtle::Lexer;
15 my $l = AtteanX::Parser::Turtle::Lexer->new( file => $fh );
16 while (my $t = $l->get_token) {
17 ...
18 }
19  
20 =head1 METHODS
21  
22 =over 4
23  
24 =cut
25  
26 50 package AtteanX::Parser::Turtle::Lexer 0.040 {
27 50 ▶ use AtteanX::Parser::Turtle::Constants;
Subroutine BEGIN: called CC=1 SCAR=0.0
28 50 ▶ use v5.14;
Subroutine BEGIN: called CC=1 SCAR=0.0
29 50 ▶ use strict;
Subroutine BEGIN: called CC=1 SCAR=0.0
30 50 ▶ use warnings;
Subroutine BEGIN: called CC=1 SCAR=0.0
31 50 ▶ use Data::Dumper;
Subroutine BEGIN: called CC=1 SCAR=0.0
32 50 ▶ use Moo;
Subroutine BEGIN: called CC=1 SCAR=0.0
33 50 ▶ use Types::Standard qw(FileHandle Ref Str Int Bool ArrayRef HashRef ConsumerOf InstanceOf);
Subroutine BEGIN: called CC=1 SCAR=0.0
34 50 ▶ use namespace::clean;
Subroutine BEGIN: called CC=1 SCAR=0.0
35  
36 50 my $r_nameChar_extra = qr'[-0-9\x{B7}\x{0300}-\x{036F}\x{203F}-\x{2040}]'o;
37 50 my $r_nameStartChar_minus_underscore = qr'[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{00010000}-\x{000EFFFF}]'o;
38 50 my $r_nameStartChar = qr/[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;
39 50 my $r_nameChar = qr/${r_nameStartChar}|[-0-9\x{b7}\x{0300}-\x{036f}\x{203F}-\x{2040}]/o;
40 50 my $r_prefixName = qr/(?:(?!_)${r_nameStartChar})(?:$r_nameChar)*/o;
41 50 my $r_nameChar_test = qr"(?:$r_nameStartChar|$r_nameChar_extra)"o;
42 50 my $r_double = qr'[+-]?([0-9]+\.[0-9]*[eE][+-]?[0-9]+|\.[0-9]+[eE][+-]?[0-9]+|[0-9]+[eE][+-]?[0-9]+)'o;
43 50 my $r_decimal = qr'[+-]?(([0-9]+\.[0-9]+)|\.([0-9])+)'o;
44 50 my $r_integer = qr'[+-]?[0-9]+'o;
45 50 my $r_PN_CHARS_U = qr/[_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;
46 50 my $r_PN_CHARS = qr"${r_PN_CHARS_U}|[-0-9\x{00B7}\x{0300}-\x{036F}\x{203F}-\x{2040}]"o;
47 50 my $r_bnode_id = qr"(?:${r_PN_CHARS_U}|[0-9])((${r_PN_CHARS}|[.])*${r_PN_CHARS})?"o;
48  
49 50 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;
50 50 my $r_PN_PREFIX = qr/(?:${r_PN_CHARS_BASE}(?:(?:${r_PN_CHARS}|[.])*${r_PN_CHARS})?)/o;
51 50 my $r_PN_LOCAL_ESCAPED = qr{(?:\\(?:[-~.!&'()*+,;=/?#@%_\$]))|%[0-9A-Fa-f]{2}}o;
52 50 our $r_PN_LOCAL = qr/(?:(?:${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;
53 50 my $r_PN_LOCAL_BNODE = qr/(?:(?:${r_PN_CHARS_U}|[0-9])(?:(?:${r_PN_CHARS}|[.])*${r_PN_CHARS})?)/o;
54 50 our $r_PNAME_NS = qr/(?:(?:${r_PN_PREFIX})?:)/o;
55 50 our $r_PNAME_LN = qr/(?:${r_PNAME_NS}${r_PN_LOCAL})/o;
56  
57 50 with 'AtteanX::API::Lexer';
58 50 has 'ignore_whitespace' => (is => 'rw', isa => Bool, default => 1);
59  
60 =item C<< new_token ( $type, $start_line, $start_column, @values ) >>
61  
62 Returns a new token with the given type and optional values, capturing the
63 current line and column of the input data.
64  
65 =cut
66  
67 470 ▶ sub new_token {
Subroutine new_token: called CC=1 SCAR=0.0
Pod documented
68 470 my $self = shift;
69 470 my $type = shift;
70 470 my $start_line = shift;
71 470 my $start_col = shift;
72 470 my $line = $self->line;
73 470 my $col = $self->column;
74 470 return AtteanX::Parser::Turtle::Token->fast_constructor( $type, $start_line, $start_col, $line, $col, \@_ );
75 }
76  
77 50 my %CHAR_TOKEN = (
78 '.' => DOT,
79 ';' => SEMICOLON,
80 '[' => LBRACKET,
81 ']' => RBRACKET,
82 '(' => LPAREN,
83 '}' => RBRACE,
84 ',' => COMMA,
85 '=' => EQUALS,
86 '~' => TILDE,
87 );
88  
89 my %METHOD_TOKEN = (
90 # q[#] => '_get_comment',
91 q[@] => '_get_keyword',
92 q[<] => '_get_iriref_or_ltlt',
93 q[>] => '_get_gtgt',
94 q[)] => '_get_rparen_or_pgtgt',
95 q[|] => '_get_rannot',
96 q[{] => '_get_lbrace_or_lannot',
97 q[_] => '_get_bnode',
98 q['] => '_get_single_literal',
99 q["] => '_get_double_literal',
100 q[:] => '_get_pname',
101 50 (map {$_ => '_get_number'} (0 .. 9, '-', '+'))
102 );
103  
104 =item C<< get_token >>
105  
106 Returns the next token present in the input.
107  
108 =cut
109  
110 503 ▶ sub get_token {
Subroutine get_token: called CC=20 SCAR=36.6
Pod documented
111 503 my $self = shift;
112 503 while (1) {
113 978 ▶ $self->fill_buffer unless (length($self->buffer));
Branch: 1 branch
BranchTrueFalseTotal
unless length $self->buffer 115 863 978
114  
115 978 my $start_column = $self->column;
116 978 my $start_line = $self->line;
117
118 978 ▶ if ($self->buffer =~ /^[ \r\n\t]+/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^[ \r\n\t]+/ou) 475 503 978
119 475 my $ws = $self->read_length($+[0]);
120 # we're ignoring whitespace tokens, but we could return them here instead of falling through to the 'next':
121 475 ▶ unless ($self->ignore_whitespace) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($self->ignore_whitespace) 0 475 475
122 0 return $self->new_token(WS, $start_line, $start_column, $ws);
123 }
124 475 next;
125 }
126  
127 503 my $c = $self->peek_char();
128 503 ▶ return unless (defined($c));
Branch: 1 branch
BranchTrueFalseTotal
unless defined $c 32 471 503
129  
130 471 ▶ if ($c eq '#') {
Branch: 1 branch
BranchTrueFalseTotal
if ($c eq "#") 0 471 471
131 # we're ignoring comment tokens, but we could return them here instead of falling through to the 'next':
132 0 $self->_get_comment();
133 0 next;
134 }
135
136 471 $self->start_column( $start_column );
137 471 $self->start_line( $start_line );
138
139 471 ▶ if ($c eq '.' and $self->buffer =~ /^$r_decimal/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($c eq "." and $self->buffer =~ /^$r_decimal/u) 0 471 471
Condition66%2/3
$c eq "." and $self->buffer =~ /^$r_decimal/u
!ll&&!rl&&r
390810
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
140 0 return $self->_get_number();
141 }
142
143 471 ▶ if ($c eq '[' and $self->buffer =~ /^\[\s*\]/) {
Branch: 5 branches
BranchTrueFalseTotal
if ($c eq '[' and $self->buffer =~ /^\[\s*\]/u) { } 2 469 471
elsif (defined(my $name = $CHAR_TOKEN{$c})) { } 129 340 469
elsif (defined(my $method = $METHOD_TOKEN{$c})) { } 220 120 340
elsif ($c =~ /[A-Za-z\x{00C0}-\x{00D6}\x{00D8}-\x{00F6}\x{00F8}-\x{02FF}\x{0370}-\x{037D}\x{037F}-\x{1FFF}\x{200C}-\x{200D}\x{2070}-\x{218F}\x{2C00}-\x{2FEF}\x{3001}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFFD}\x{10000}-\x{EFFFF}]/ou) { } 120 0 120
elsif ($c eq '^') { } 0 0 0
Condition100%3/3
$c eq "[" and $self->buffer =~ /^\[\s*\]/u
!ll&&!rl&&r
46542
MC/DC100%2/2
$c eq "[" and $self->buffer =~ /^\[\s*\]/u
$c eq "[" $self->buffer =~ /^\[\s*\]/u
Truth table100%3/3
A and B
A= $c eq "["B= $self->buffer =~ /^\[\s*\]/u
ABresult
0X0
100
111
144 2 $self->read_length($+[0]);
145 2 return $self->new_token(ANON, $start_line, $start_column, '[]');
146 129 } elsif (defined(my $name = $CHAR_TOKEN{$c})) { $self->get_char; return $self->new_token($name, $start_line, $start_column, $c); }
147 220 elsif (defined(my $method = $METHOD_TOKEN{$c})) { return $self->$method() }
148 elsif ($c =~ /[A-Za-z\x{00C0}-\x{00D6}\x{00D8}-\x{00F6}\x{00F8}-\x{02FF}\x{0370}-\x{037D}\x{037F}-\x{1FFF}\x{200C}-\x{200D}\x{2070}-\x{218F}\x{2C00}-\x{2FEF}\x{3001}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFFD}\x{10000}-\x{EFFFF}]/o) {
149 120 ▶ if ($self->buffer =~ /^a(?!:)\s/o) {
Branch: 6 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^a(?!:)\s/ou) { } 22 98 120
elsif ($self->buffer =~ /^(?:true|false)(?!:)\b/ou) { } 0 98 98
elsif ($self->buffer =~ /^BASE(?!:)\b/iou) { } 0 98 98
elsif ($self->buffer =~ /^PREFIX(?!:)\b/iou) { } 0 98 98
elsif ($self->buffer =~ /^VERSION(?!:)\b/iou) { } 0 98 98
elsif ($self->buffer =~ /^GRAPH(?!:)\b/iou) { } 0 98 98
150 22 $self->get_char;
151 22 return $self->new_token(A, $start_line, $start_column, 'a');
152 } elsif ($self->buffer =~ /^(?:true|false)(?!:)\b/o) {
153 0 my $bool = $self->read_length($+[0]);
154 0 return $self->new_token(BOOLEAN, $start_line, $start_column, $bool);
155 } elsif ($self->buffer =~ /^BASE(?!:)\b/oi) {
156 0 $self->read_length(4);
157 0 return $self->new_token(BASE, $start_line, $start_column);
158 } elsif ($self->buffer =~ /^PREFIX(?!:)\b/io) {
159 0 $self->read_length(6);
160 0 return $self->new_token(PREFIX, $start_line, $start_column);
161 } elsif ($self->buffer =~ /^VERSION(?!:)\b/io) {
162 0 $self->read_length(7);
163 0 return $self->new_token(VERSION, $start_line, $start_column);
164 } elsif ($self->buffer =~ /^GRAPH(?!:)\b/io) {
165 0 $self->read_length(5);
166 0 return $self->new_token(GRAPH, $start_line, $start_column);
167 } else {
168 98 return $self->_get_pname;
169 }
170 }
171 elsif ($c eq '^') {
172 0 $self->read_word('^^'); return $self->new_token(HATHAT, $start_line, $start_column); }
173 else {
174 # Carp::cluck sprintf("Unexpected byte '$c' (0x%02x)", ord($c));
175 0 return $self->_throw_error(sprintf("Unexpected byte '%s' (0x%02x)", $c, ord($c)));
176 }
177 0 warn sprintf('byte: 0x%x', ord($c));
178 }
179 }
180  
181 =begin private
182  
183 =cut
184  
185  
186 126 ▶ sub _get_pname {
Subroutine _get_pname: called CC=3 SCAR=11.0
187 126 my $self = shift;
188 126 my $prefix = '';
189
190 126 ▶ if ($self->buffer =~ /^$r_PNAME_LN/o) {
Branch: 2 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^$AtteanX::Parser::Turtle::Lexer::r_PNAME_LN/ou) { } 95 31 126
elsif ($self->buffer =~ /^$AtteanX::Parser::Turtle::Lexer::r_PNAME_NS/u) { } 31 0 31
191 95 my $ln = $self->read_length($+[0]);
192 95 my ($ns, $local) = ($ln =~ /^([^:]*:)(.*)$/);
193 50 ▶ no warnings 'uninitialized';
Subroutine BEGIN: called CC=1 SCAR=0.0
194 95 $local =~ s{\\([-~.!&'()*+,;=:/?#@%_\$])}{$1}g;
195 95 return $self->new_token(PREFIXNAME, $self->start_line, $self->start_column, $ns, $local);
196 } elsif ($self->buffer =~ /^$r_PNAME_NS/) {
197 31 my $ns = $self->read_length($+[0]);
198 31 return $self->new_token(PREFIXNAME, $self->start_line, $self->start_column, $ns);
199 } else {
200 0 $self->_throw_error("Invalid PrefixedName");
201 }
202 }
203  
204 0 ▶ sub _get_gtgt {
Subroutine _get_gtgt: not called CC=1 SCAR=6.9
205 0 my $self = shift;
206 0 $self->read_word('>>');
207 0 return $self->new_token(GTGT, $self->start_line, $self->start_column, '>>');
208 }
209
210 0 ▶ sub _get_lbrace_or_lannot {
Subroutine _get_lbrace_or_lannot: not called CC=2 SCAR=17.9
211 0 my $self = shift;
212 0 $self->get_char_safe(q[{]);
213 0 ▶ if ($self->buffer =~ /^\|/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^\|/ou) 0 0 0
214 0 $self->get_char_safe(q[|]);
215 0 return $self->new_token(LANNOT, $self->start_line, $self->start_column, '{|');
216 }
217 0 return $self->new_token(LBRACE, $self->start_line, $self->start_column, '{');
218 }
219
220 0 ▶ sub _get_rannot {
Subroutine _get_rannot: not called CC=1 SCAR=6.9
221 0 my $self = shift;
222 0 $self->read_word('|}');
223 0 return $self->new_token(RANNOT, $self->start_line, $self->start_column, '|}');
224 }
225
226 1 ▶ sub _get_rparen_or_pgtgt {
Subroutine _get_rparen_or_pgtgt: called CC=2 SCAR=8.5
227 1 my $self = shift;
228 1 $self->get_char_safe(q[)]);
229 1 ▶ if ($self->buffer =~ /^>>/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^>>/ou) { } 0 1 1
230 0 $self->get_char_safe(q[>]);
231 0 $self->get_char_safe(q[>]);
232 0 return $self->new_token(PGTGT, $self->start_line, $self->start_column, 'PGTGT');
233 } else {
234 1 return $self->new_token(RPAREN, $self->start_line, $self->start_column, ')');
235 }
236 }
237
238 89 ▶ sub _get_iriref_or_ltlt {
Subroutine _get_iriref_or_ltlt: called CC=15 SCAR=50.3
239 89 my $self = shift;
240 89 $self->get_char_safe(q[<]);
241 89 ▶ if ($self->buffer =~ /^<\(/o) {
Branch: 2 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^<\(/ou) { } 0 89 89
elsif ($self->buffer =~ /^</ou) { } 0 89 89
242 0 $self->get_char_safe(q[<]);
243 0 $self->get_char_safe(q[(]);
244 0 return $self->new_token(LTLTP, $self->start_line, $self->start_column, '<<(');
245 } elsif ($self->buffer =~ /^</o) {
246 0 $self->get_char_safe(q[<]);
247 0 return $self->new_token(LTLT, $self->start_line, $self->start_column, '<<');
248 }
249
250 89 ▶ if ($self->buffer =~ m/^[\x23-\x3d\x3f-\x5a\x5d-\x7e]*>/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^[\x23-\x3d\x3f-\x5a\x5d-\x7e]*>/ou) 89 0 89
251 89 my $iri .= $self->read_length($+[0]);
252 89 chop($iri);
253 89 return $self->new_token(IRI, $self->start_line, $self->start_column, $iri);
254 }
255
256 0 my $iri = '';
257 0 while (1) {
258 0 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 0 0
259 0 my $c = $self->peek_char;
260 0 ▶ last unless defined($c);
Branch: 1 branch
BranchTrueFalseTotal
unless defined $c 0 0 0
261 }
262 0 ▶ if (substr($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
263 0 $self->get_char_safe('\\');
264 0 my $esc = $self->get_char;
265 0 ▶ if ($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
266 0 $iri .= "\\";
267 } elsif ($esc eq 'U') {
268 0 my $codepoint = $self->read_length(8);
269 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
270 0 $iri .= $self->unescape_hex($codepoint);
271 } elsif ($esc eq 'u') {
272 0 my $codepoint = $self->read_length(4);
273 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
274 0 my $char = $self->unescape_hex($codepoint);
275 0 ▶ if ($char =~ /[<>" {}|\\^`]/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($char =~ /[<>" {}|\\^`]/ou) 0 0 0
276 0 $self->_throw_error(sprintf("Bad IRI character: '%s' (0x%x)", $char, ord($char)));
277 }
278 0 $iri .= $char;
279 } else {
280 0 $self->_throw_error("Unrecognized iri escape '$esc'");
281 }
282 } elsif ($self->buffer =~ /^[^<>\x00-\x20\\"{}|^`]+/o) {
283 0 $iri .= $self->read_length($+[0]);
284 } elsif (substr($self->buffer, 0, 1) eq '>') {
285 0 last;
286 } else {
287 0 my $c = $self->peek_char;
288 0 $self->_throw_error("Got '$c' while expecting IRI character");
289 }
290 }
291 0 $self->get_char_safe(q[>]);
292 0 return $self->new_token(IRI, $self->start_line, $self->start_column, $iri);
293 }
294  
295 5 ▶ sub unescape_hex {
Subroutine unescape_hex: called CC=3 SCAR=11.0
Pod undocumented
296 5 my $self = shift;
297 5 my $codepoint = shift;
298 5 my $cp = hex($codepoint);
299 5 ▶ if ($cp >= 0xd800 && $cp <= 0xdfff) {
Branch: 1 branch
BranchTrueFalseTotal
if ($cp >= 55296 and $cp <= 57343) 1 4 5
Condition66%2/3
$cp >= 55296 and $cp <= 57343
!ll&&!rl&&r
401
MC/DC50%1/2
$cp >= 55296 and $cp <= 57343
$cp >= 55296 $cp <= 57343
Truth table66%2/3
A and B
A= $cp >= 55296B= $cp <= 57343
ABresult
0X0
100
111
300 1 $self->_throw_error("Invalid use of surrogate codepoint in escape sequence: '$codepoint'", $codepoint);
301 }
302 4 return chr($cp);
303 }
304
305 24 ▶ sub _get_bnode {
Subroutine _get_bnode: called CC=2 SCAR=7.0
306 24 my $self = shift;
307 24 $self->read_word('_:');
308 24 ▶ $self->_throw_error("Expected: name") unless ($self->buffer =~ /^${r_bnode_id}/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $self->buffer =~ /^$r_bnode_id/ou 0 24 24
309 24 my $name = substr($self->buffer, 0, $+[0]);
310 24 $self->read_word($name);
311 24 return $self->new_token(BNODE, $self->start_line, $self->start_column, $name);
312 }
313  
314 10 ▶ sub _get_number {
Subroutine _get_number: called CC=4 SCAR=17.9
315 10 my $self = shift;
316 10 ▶ if ($self->buffer =~ /^${r_double}/o) {
Branch: 3 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^$r_double/ou) { } 0 10 10
elsif ($self->buffer =~ /^$r_decimal/ou) { } 0 10 10
elsif ($self->buffer =~ /^$r_integer/ou) { } 10 0 10
317 0 return $self->new_token(DOUBLE, $self->start_line, $self->start_column, $self->read_length($+[0]));
318 } elsif ($self->buffer =~ /^${r_decimal}/o) {
319 0 return $self->new_token(DECIMAL, $self->start_line, $self->start_column, $self->read_length($+[0]));
320 } elsif ($self->buffer =~ /^${r_integer}/o) {
321 10 return $self->new_token(INTEGER, $self->start_line, $self->start_column, $self->read_length($+[0]));
322 }
323 0 $self->_throw_error("Expected number");
324 }
325  
326 0 ▶ sub _get_comment {
Subroutine _get_comment: not called CC=5 SCAR=34.0
327 0 my $self = shift;
328 0 $self->get_char_safe('#');
329 0 my $comment = '';
330 0 my $c = $self->peek_char;
331 0 ▶ while (length($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
332 0 $comment .= $self->get_char;
333 0 $c = $self->peek_char;
334 }
335 0 ▶ if (length($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
336 0 $self->get_char;
337 }
338 0 return $self->new_token(COMMENT, $self->start_line, $self->start_column, $comment);
339 }
340  
341 26 ▶ sub _get_double_literal {
Subroutine _get_double_literal: called CC=13 SCAR=28.5
342 26 my $self = shift;
343 # my $c = $self->peek_char();
344 26 $self->get_char_safe(q["]);
345 26 ▶ if (substr($self->buffer, 0, 2) eq q[""]) {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 2) eq '""') { } 3 23 26
346 # #x22 #x22 #x22 lcharacter* #x22 #x22 #x22
347 3 $self->read_word(q[""]);
348
349 3 my $quote_count = 0;
350 3 my $string = '';
351 3 while (1) {
352 12 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 12 12
353 0 $self->fill_buffer;
354 0 ▶ $self->_throw_error("Found EOF in string literal") if (length($self->buffer) == 0);
Branch: 1 branch
BranchTrueFalseTotal
if length $self->buffer == 0 0 0 0
355 }
356 12 ▶ if (substr($self->buffer, 0, 1) eq '"') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '"') { } 9 3 12
357 9 my $c = $self->get_char;
358 9 $quote_count++;
359 9 ▶ last if ($quote_count == 3);
Branch: 1 branch
BranchTrueFalseTotal
if $quote_count == 3 3 6 9
360 } else {
361 3 ▶ if ($quote_count) {
Branch: 1 branch
BranchTrueFalseTotal
if ($quote_count) 0 3 3
362 0 $string .= '"' foreach (1..$quote_count);
363 0 $quote_count = 0;
364 }
365 3 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 0 3 3
366 0 $string .= $self->_get_escaped_char();
367 } else {
368 3 $self->{buffer} =~ /^[^"\\]+/;
369 3 $string .= $self->read_length($+[0]);
370 }
371 }
372 }
373 3 return $self->new_token(STRING3D, $self->start_line, $self->start_column, $string);
374 } else {
375 ### #x22 scharacter* #x22
376 23 my $string = '';
377 23 while (1) {
378 46 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 1 45 46
elsif ($self->buffer =~ /^[^"\\]+/ou) { } 22 23 45
elsif (substr($self->buffer, 0, 1) eq '"') { } 23 0 23
379 1 my $c = $self->_get_escaped_char();
380 1 $string .= $c;
381 } elsif ($self->buffer =~ /^[^"\\]+/o) {
382 22 my $s = $self->read_length($+[0]);
383 22 $string .= $s;
384 } elsif (substr($self->buffer, 0, 1) eq '"') {
385 23 last;
386 } else {
387 0 my $c = $self->peek_char;
388 0 ▶ if (defined($c)) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $c) { } 0 0 0
389 0 $self->_throw_error("Got '$c' while expecting string character");
390 } else {
391 0 $self->_throw_error("Got EOF while expecting string character");
392 }
393 }
394 }
395 23 $self->get_char_safe(q["]);
396 23 return $self->new_token(STRING1D, $self->start_line, $self->start_column, $string);
397 }
398 }
399  
400 7 ▶ sub _get_single_literal {
Subroutine _get_single_literal: called CC=14 SCAR=30.7
401 7 my $self = shift;
402 7 $self->get_char_safe("'");
403 7 ▶ if (substr($self->buffer, 0, 2) eq q['']) {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 2) eq q['']) { } 2 5 7
404 # #x22 #x22 #x22 lcharacter* #x22 #x22 #x22
405 2 $self->read_word(q['']);
406
407 2 my $quote_count = 0;
408 2 my $string = '';
409 2 while (1) {
410 8 ▶ if (length($self->buffer) == 0) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $self->buffer == 0) 0 8 8
411 0 $self->fill_buffer;
412 0 ▶ $self->_throw_error("Found EOF in string literal") if (length($self->buffer) == 0);
Branch: 1 branch
BranchTrueFalseTotal
if length $self->buffer == 0 0 0 0
413 }
414 8 ▶ if (substr($self->buffer, 0, 1) eq "'") {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq q[']) { } 6 2 8
415 6 my $c = $self->get_char;
416 6 $quote_count++;
417 6 ▶ last if ($quote_count == 3);
Branch: 1 branch
BranchTrueFalseTotal
if $quote_count == 3 2 4 6
418 } else {
419 2 ▶ if ($quote_count) {
Branch: 1 branch
BranchTrueFalseTotal
if ($quote_count) 0 2 2
420 0 $string .= "'" foreach (1..$quote_count);
421 0 $quote_count = 0;
422 }
423 2 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 1 branch
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 0 2 2
424 0 $string .= $self->_get_escaped_char();
425 } else {
426 2 $self->{buffer} =~ /^[^'\\]+/;
427 2 $string .= $self->read_length($+[0]);
428 }
429 }
430 }
431 2 return $self->new_token(STRING3S, $self->start_line, $self->start_column, $string);
432 } else {
433 ### #x22 scharacter* #x22
434 5 my $string = '';
435 5 while (1) {
436 10 ▶ $self->fill_buffer unless (length($self->buffer));
Branch: 1 branch
BranchTrueFalseTotal
unless length $self->buffer 0 10 10
437 10 ▶ if (substr($self->buffer, 0, 1) eq '\\') {
Branch: 3 branches
BranchTrueFalseTotal
if (substr($self->buffer, 0, 1) eq '\\') { } 6 4 10
elsif ($self->buffer =~ /^[^'\\]+/ou) { } 0 4 4
elsif (substr($self->buffer, 0, 1) eq q[']) { } 4 0 4
438 6 $string .= $self->_get_escaped_char();
439 } elsif ($self->buffer =~ /^[^'\\]+/o) {
440 0 $string .= $self->read_length($+[0]);
441 } elsif (substr($self->buffer, 0, 1) eq "'") {
442 4 last;
443 } else {
444 0 my $c = $self->peek_char();
445 0 ▶ if (defined($c)) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $c) { } 0 0 0
446 0 $self->_throw_error("Got '$c' while expecting string character");
447 } else {
448 0 $self->_throw_error("Got EOF while expecting string character");
449 }
450 }
451 }
452 4 $self->get_char_safe(q[']);
453 4 return $self->new_token(STRING1S, $self->start_line, $self->start_column, $string);
454 }
455 }
456  
457 7 ▶ sub _get_escaped_char {
Subroutine _get_escaped_char: called CC=12 SCAR=30.2
458 7 my $self = shift;
459 7 my $c = $self->peek_char;
460 7 $self->get_char_safe('\\');
461 7 my $esc = $self->get_char;
462 0 ▶ if ($esc eq '\\') { return "\\" }
Branch: 9 branches
BranchTrueFalseTotal
if ($esc eq '\\') { } 0 7 7
elsif ($esc =~ /^['">]$/u) { } 2 5 7
elsif ($esc eq 'r') { } 0 5 5
elsif ($esc eq 't') { } 0 5 5
elsif ($esc eq 'n') { } 0 5 5
elsif ($esc eq 'b') { } 0 5 5
elsif ($esc eq 'f') { } 0 5 5
elsif ($esc eq 'U') { } 2 3 5
elsif ($esc eq 'u') { } 3 0 3
463 2 elsif ($esc =~ /^['">]$/) { return $esc }
464 0 elsif ($esc eq 'r') { return "\r" }
465 0 elsif ($esc eq 't') { return "\t" }
466 0 elsif ($esc eq 'n') { return "\n" }
467 0 elsif ($esc eq 'b') { return "\b" }
468 0 elsif ($esc eq 'f') { return "\f" }
469 elsif ($esc eq 'U') {
470 2 my $codepoint = $self->read_length(8);
471 2 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($codepoint =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $codepoint =~ /^[0-9A-Fa-f]+$/ou 0 2 2
472 2 return $self->unescape_hex($codepoint);
473 } elsif ($esc eq 'u'){
474 3 my $codepoint = $self->read_length(4);
475 3 ▶ $self->_throw_error("Bad unicode escape codepoint '$codepoint'") unless ($codepoint =~ /^[0-9A-Fa-f]+$/o);
Branch: 1 branch
BranchTrueFalseTotal
unless $codepoint =~ /^[0-9A-Fa-f]+$/ou 0 3 3
476 3 return $self->unescape_hex($codepoint);
477 }
478 0 $self->_throw_error("Unrecognized string escape '$esc'");
479 }
480
481 35 ▶ sub _get_keyword {
Subroutine _get_keyword: called CC=7 SCAR=23.8
482 35 my $self = shift;
483 35 $self->get_char_safe('@');
484 35 ▶ if ($self->buffer =~ /^base/o) {
Branch: 3 branches
BranchTrueFalseTotal
if ($self->buffer =~ /^base/ou) { } 0 35 35
elsif ($self->buffer =~ /^prefix/ou) { } 31 4 35
elsif ($self->buffer =~ /^version/ou) { } 0 4 4
485 0 $self->read_word('base');
486 0 return $self->new_token(TURTLEBASE, $self->start_line, $self->start_column);
487 } elsif ($self->buffer =~ /^prefix/o) {
488 31 $self->read_word('prefix');
489 31 return $self->new_token(TURTLEPREFIX, $self->start_line, $self->start_column);
490 } elsif ($self->buffer =~ /^version/o) {
491 0 $self->read_word('version');
492 0 return $self->new_token(TURTLEVERSION, $self->start_line, $self->start_column);
493 } else {
494 4 ▶ if ($self->buffer =~ /^[a-zA-Z]+(-[a-zA-Z0-9]+)*(--[a-zA-Z]+)?\b/o) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->buffer =~ /^[a-zA-Z]+(-[a-zA-Z0-9]+)*(--[a-zA-Z]+)?\b/ou) 4 0 4
495 4 my $lang = $self->read_length($+[0]);
496 4 ▶ if ($lang !~ /--(ltr|rtl)$/ and $lang =~ /--(\w+)$/) {
Branch: 1 branch
BranchTrueFalseTotal
if (not $lang =~ /--(ltr|rtl)$/u and $lang =~ /--(\w+)$/u) 0 4 4
Condition33%1/3
not $lang =~ /--(ltr|rtl)$/u and $lang =~ /--(\w+)$/u
!ll&&!rl&&r
040
MC/DC0%0/2
not $lang =~ /--(ltr|rtl)$/u and $lang =~ /--(\w+)$/u
not $lang =~ /--(ltr|rtl)$/u $lang =~ /--(\w+)$/u
Truth table33%1/3
not(A) and B
A= not $lang =~ /--(ltr|rtl)$/uB= $lang =~ /--(\w+)$/u
ABresult
0X0
100
111
497 0 $self->_throw_error("Expected base direction to be 'ltr' or 'rtl', but found '$1'");
498 }
499 4 return $self->new_token(LANG, $self->start_line, $self->start_column, $lang);
500 }
501 0 $self->_throw_error("Expected keyword or language tag");
502 }
503 }
504  
505 1 ▶ sub _throw_error {
Subroutine _throw_error: called CC=4 SCAR=14.2
506 1 my $self = shift;
507 1 my $error = shift;
508 1 ▶ my $text = shift // '';
Condition50%1/2
shift() // ""
l!l
10
MC/DC0%0/1
shift() // ""
shift()
Truth table50%1/2
A
A= shift()
Aresult
11
00
509 1 my $len = length($text);
510 1 my $line = $self->line;
511 1 my $col = $self->column;
512 1 my $loc = "at $line:$col";
513 1 ▶ if ($len > 0) {
Branch: 1 branch
BranchTrueFalseTotal
if ($len > 0) 1 0 1
514 1 ▶ if ($col >= $len) {
Branch: 1 branch
BranchTrueFalseTotal
if ($col >= $len) { } 1 0 1
515 1 $col -= $len;
516 1 $loc = "at $line:$col";
517 } else {
518 0 $loc = "near $line:$col"
519 }
520 }
521 1 Carp::confess "$error $loc with buffer: " . Dumper($self->buffer);
522 }
523 }
524  
525 50 1;
526  
527 __END__
« AtteanX/Parser/NTuples.pm ↑ Summary AtteanX/Serializer/TurtleTokens.pm »