Minor improvements by introducing getters and setters instead of combinators
Change-Id: Ifcc801bab9ae8d085cef492880e81b7c0c71d19c
diff --git a/lib/KorAP/XML/Annotation/DGD/Structure.pm b/lib/KorAP/XML/Annotation/DGD/Structure.pm
index a2192ae..4b49349 100644
--- a/lib/KorAP/XML/Annotation/DGD/Structure.pm
+++ b/lib/KorAP/XML/Annotation/DGD/Structure.pm
@@ -76,7 +76,7 @@
p_end => $_->[0],
pti => 64
);
- $mt->payload('<b>1');
+ $mt->set_payload('<b>1');
$sentences++;
$p_start = $_->[0];
diff --git a/lib/KorAP/XML/Annotation/DeReKo/Structure.pm b/lib/KorAP/XML/Annotation/DeReKo/Structure.pm
index cc2b751..d56173a 100644
--- a/lib/KorAP/XML/Annotation/DeReKo/Structure.pm
+++ b/lib/KorAP/XML/Annotation/DeReKo/Structure.pm
@@ -63,7 +63,7 @@
my $pl;
$pl .= '<b>' . ($level ? $level - 1 : 0);
$pl .= '<s>' . $tui if $tui;
- $mt->payload($pl);
+ $mt->set_payload($pl);
};
# Use sentence and paragraph elements for base
@@ -72,8 +72,8 @@
if ($name eq 's' && index($as_base, 'sentences') >= 0) {
# Clone Multiterm
my $mt2 = $mt->clone;
- $mt2->term('<>:base/s:' . $name);
- $mt2->payload('<b>2');
+ $mt2->set_term('<>:base/s:' . $name);
+ $mt2->set_payload('<b>2');
$sentences++;
# Add to stream
@@ -82,8 +82,8 @@
elsif ($name eq 'p' && index($as_base, 'paragraphs') >= 0) {
# Clone Multiterm
my $mt2 = $mt->clone;
- $mt2->term('<>:base/s:' . $name);
- $mt2->payload('<b>1');
+ $mt2->set_term('<>:base/s:' . $name);
+ $mt2->set_payload('<b>1');
$paragraphs++;
# Add to stream
@@ -95,8 +95,8 @@
if (my $nr = first { $_->{-name} eq 'n' } @$attrs) {
if (($nr = $nr->{'#text'}) && looks_like_number($nr)) {
my $mt2 = $mtt->add('~:base/s:pb');
- $mt2->payload('<i>' . $nr . '<i>' . $span->o_start);
- $mt2->store_offsets(0);
+ $mt2->set_payload('<i>' . $nr . '<i>' . $span->o_start);
+ $mt2->set_stored_offsets(0);
};
};
};
diff --git a/lib/KorAP/XML/Annotation/RWK/Structure.pm b/lib/KorAP/XML/Annotation/RWK/Structure.pm
index 82de1c7..0d1bb2f 100644
--- a/lib/KorAP/XML/Annotation/RWK/Structure.pm
+++ b/lib/KorAP/XML/Annotation/RWK/Structure.pm
@@ -88,7 +88,7 @@
p_end => $_->[0],
pti => 64
);
- $mt->payload('<b>1');
+ $mt->set_payload('<b>1');
if ($type eq 's') {
$sentences++;
diff --git a/lib/KorAP/XML/Index/MultiTerm.pm b/lib/KorAP/XML/Index/MultiTerm.pm
index 7e089de..90253e5 100644
--- a/lib/KorAP/XML/Index/MultiTerm.pm
+++ b/lib/KorAP/XML/Index/MultiTerm.pm
@@ -6,143 +6,155 @@
# Todo: This should store only the pti and the payload - with clever access using the pti!
# Everything should be stored as bytes already (if this is feasible)
+use constant {
+ PAYLOAD => 0,
+ P_START => 1,
+ P_END => 2,
+ O_START => 3,
+ O_END => 4,
+ TERM => 5,
+ STORED_OFFSETS => 6,
+ PTI => 7, # former 10
+ TUI => 8,
+};
+
sub new {
my $self = bless [], shift;
- my $i = 0;
- for (; $i < scalar @_; $i+=2) {
+ for (my $i = 0; $i < scalar @_; $i+=2) {
if ($_[$i] eq 'term') {
- $self->term($_[$i+1]);
+ $self->[TERM] = $_[$i+1];
}
elsif ($_[$i] eq 'p_start') {
- $self->p_start($_[$i+1]);
+ $self->[P_START] = $_[$i+1];
}
elsif ($_[$i] eq 'p_end') {
- $self->p_end($_[$i+1]);
+ $self->[P_END] = $_[$i+1];
}
elsif ($_[$i] eq 'payload') {
- $self->payload($_[$i+1]);
+ $self->[PAYLOAD] = $_[$i+1];
}
elsif ($_[$i] eq 'store_offsets') {
$self->store_offsets($_[$i+1]);
}
elsif ($_[$i] eq 'o_start') {
- $self->o_start($_[$i+1]);
+ $self->[O_START] = $_[$i+1];
}
elsif ($_[$i] eq 'o_end') {
- $self->o_end($_[$i+1]);
+ $self->[O_END] = $_[$i+1];
}
elsif ($_[$i] eq 'pti') {
- $self->pti($_[$i+1]);
+ $self->[PTI] = $_[$i+1];
}
elsif ($_[$i] eq 'tui') {
- $self->tui($_[$i+1]);
+ $self->[TUI] = $_[$i+1];
};
};
$self;
};
-# 0
-sub payload {
- if (defined $_[1]) {
- return $_[0]->[0] = $_[1];
- };
- $_[0]->[0];
+sub set_payload {
+ return $_[0]->[PAYLOAD] = $_[1];
};
-# 1
-sub p_start {
- if (defined $_[1]) {
- return $_[0]->[1] = $_[1];
- };
- $_[0]->[1] // 0;
+sub get_payload {
+ $_[0]->[PAYLOAD];
};
-# 2
-sub p_end {
- if (defined $_[1]) {
- return $_[0]->[2] = $_[1];
- };
- $_[0]->[2] // 0;
+sub set_p_start {
+ return $_[0]->[P_START] = $_[1];
};
-# 3
-sub o_start {
- if (defined $_[1]) {
- return $_[0]->[3] = $_[1];
- };
- $_[0]->[3] // 0;
+sub get_p_start {
+ $_[0]->[P_START] // 0;
};
-# 4
-sub o_end {
- if (defined $_[1]) {
- return $_[0]->[4] = $_[1];
- };
- $_[0]->[4] // 0;
+sub set_p_end {
+ $_[0]->[P_END] = $_[1];
};
-# 5
-sub term {
- if (defined $_[1]) {
- return $_[0]->[5] = $_[1];
- };
- $_[0]->[5] // '';
+sub get_p_end {
+ $_[0]->[P_END] // 0
};
-# 6
-sub store_offsets {
- if (defined $_[1]) {
- return $_[0]->[6] = $_[1];
- };
- $_[0]->[6];
+sub set_o_start {
+ return $_[0]->[O_START] = $_[1];
};
-# pti
-sub pti {
- if (defined $_[1]) {
- return $_[0]->[10] = $_[1];
- };
- $_[0]->[10];
+sub get_o_start {
+ $_[0]->[O_START] // 0;
};
-# Not serialized - just setter/getter
-sub tui {
- if (defined $_[1]) {
- return $_[0]->[11] = $_[1];
- };
- $_[0]->[11];
+sub set_o_end {
+ $_[0]->[O_END] = $_[1];
};
+sub get_o_end {
+ $_[0]->[O_END] // 0;
+};
+
+sub set_term {
+ return $_[0]->[TERM] = $_[1];
+};
+
+sub get_term {
+ $_[0]->[TERM] // '';
+};
+
+sub set_stored_offsets {
+ return $_[0]->[STORED_OFFSETS] = $_[1];
+};
+
+sub get_stored_offsets {
+ $_[0]->[STORED_OFFSETS];
+};
+
+sub set_pti {
+ return $_[0]->[PTI] = $_[1];
+};
+
+sub get_pti {
+ $_[0]->[PTI];
+};
+
+sub set_tui {
+ return $_[0]->[TUI] = $_[1];
+};
+
+sub get_tui {
+ $_[0]->[TUI];
+};
+
+
# To string based on array
sub to_string {
- my $string = _escape_term($_[0]->[5]);
+ my $string = _escape_term($_[0]->[TERM]);
my $pre;
# PTI
- $pre .= '<b>' . $_[0]->[10] if $_[0]->[10];
+ $pre .= '<b>' . $_[0]->[PTI] if $_[0]->[PTI];
# Offsets
- if (defined $_[0]->[3]) {
- $pre .= '<i>' .$_[0]->[3] .
- '<i>' . $_[0]->[4];
+ if (defined $_[0]->[O_START]) {
+ $pre .= '<i>' .$_[0]->[O_START] .
+ '<i>' . $_[0]->[O_END];
};
# my $pl = $_[0]->[1] ?
# $_[0]->[1] - 1 : $_[0]->[0];
- if ($_[0]->[2] || $_[0]->[0]) {
+ if ($_[0]->[P_END] || $_[0]->[PAYLOAD]) {
# p_end
- if (defined $_[0]->[2]) {
- $pre .= '<i>' . $_[0]->[2];
+ if (defined $_[0]->[P_END]) {
+ $pre .= '<i>' . $_[0]->[P_END];
};
if ($_[0]->[0]) {
- if (index($_[0]->[0], '<') == 0) {
- $pre .= $_[0]->[0];
+ if (index($_[0]->[PAYLOAD], '<') == 0) {
+ $pre .= $_[0]->[PAYLOAD];
}
else {
- $pre .= '<?>' . $_[0]->[0];
+ $pre .= '<?>' . $_[0]->[PAYLOAD];
};
};
};
@@ -156,31 +168,6 @@
bless [@$self], __PACKAGE__;
};
-sub to_string_2 {
- my $self = shift;
- my $string = $self->term;
- if (defined $self->o_start) {
- $string .= '#' .$self->o_start .'-' . $self->o_end;
- };
-
- my $pl = $self->p_end ? $self->p_end - 1 : $self->payload;
- if ($self->p_end || $self->payload) {
- $string .= '$';
- if ($self->p_end) {
- $string .= '<i>' . $self->p_end;
- };
- if ($self->payload) {
- if (index($self->payload, '<') == 0) {
- $string .= $self->payload;
- }
- else {
- $string .= '<?>' . $self->payload;
- };
- };
- };
-
- return $string;
-};
sub _escape_term ($) {
my $str = shift;
@@ -189,71 +176,4 @@
};
-# DEPRECATED
-sub to_solr {
- my $self = shift;
- my $increment = shift;
-
- my (@payload_types, @payload) = ();
-
- my $term = $self->term;
- if ($term =~ s/\#(\d+)-(\d+)//) {
- push(@payload, $1, $2);
- push(@payload_types, 'l', 'l');
- };
-
- my %term = ( t => $term );
- if (defined $increment && $increment == 0) {
- $term{i} = 0;
- };
-
- if (defined $self->o_start && !@payload) {
- push(@payload, $self->o_start, $self->o_end);
- push(@payload_types, 'l', 'l');
- };
-
- if ($self->p_end || $self->payload) {
- if ($self->p_end) {
- push(@payload, $self->p_end);
- push(@payload_types, 'l');
- };
- if ($self->payload) {
- if (index($self->payload, '<') == 0) {
- my @pls = split /(?=<)|(?<=>)/, $self->payload;
- for (my $i = 0; $i < @pls; $i+=2) {
- if ($pls[$i] eq 'b') {
- push(@payload, $pls[$i+1]);
- push(@payload_types, 'c');
- }
- elsif ($pls[$i] eq 's') {
- push(@payload, $pls[$i+1]);
- push(@payload_types, 's');
- }
- elsif ($pls[$i] eq 'i') {
- push(@payload, $pls[$i+1]);
- push(@payload_types, 'l');
- }
- elsif ($pls[$i] eq 'l') {
- push(@payload, $pls[$i+1]);
- push(@payload_types, 'q');
- }
- else {
- push(@payload, $pls[$i+1]);
- push(@payload_types, 'w*');
- };
- };
- }
- else {
- push(@payload, $self->payload);
- push(@payload_types, 'w*');
- };
- };
- };
- if (@payload) {
- $term{p} = encode_base64(pack(join('', @payload_types), @payload), '');
- };
-
- return \%term;
-};
-
1;
diff --git a/lib/KorAP/XML/Index/MultiTermToken.pm b/lib/KorAP/XML/Index/MultiTermToken.pm
index 3556422..2815eff 100644
--- a/lib/KorAP/XML/Index/MultiTermToken.pm
+++ b/lib/KorAP/XML/Index/MultiTermToken.pm
@@ -10,6 +10,13 @@
# but is rather slow on sorting relations.
# Should be replaced by an efficient implementation!
+use constant {
+ MT => 0,
+ O_START => 1,
+ O_END => 2,
+ ID_COUNTER => 3
+};
+
sub new {
bless [], shift;
};
@@ -30,33 +37,30 @@
else {
$mt = $_[0];
};
- $self->[0] //= [];
- push(@{$self->[0]}, $mt);
+ $self->[MT] //= [];
+ push(@{$self->[MT]}, $mt);
$mt;
};
-# 0 -> mt
-
-# 1
-sub o_start {
- if (defined $_[1]) {
- return $_[0]->[1] = $_[1];
- };
- $_[0]->[1];
+sub set_o_start {
+ return $_[0]->[O_START] = $_[1];
};
-# 2
-sub o_end {
- if (defined $_[1]) {
- return $_[0]->[2] = $_[1];
- };
- $_[0]->[2];
+sub get_o_start {
+ $_[0]->[O_START]
};
-# 3: Return a new term id
+sub set_o_end {
+ return $_[0]->[O_END] = $_[1];
+};
+
+sub get_o_end {
+ $_[0]->[O_END]
+};
+
sub id_counter {
- $_[0]->[3] //= 1;
- return $_[0]->[3]++;
+ $_[0]->[ID_COUNTER] //= 1;
+ return $_[0]->[ID_COUNTER]++;
};
sub surface {
@@ -85,7 +89,7 @@
sub to_string {
my $self = shift;
- my $string = '[(' . $self->o_start . '-'. $self->o_end . ')';
+ my $string = '[(' . $self->get_o_start . '-'. $self->get_o_end . ')';
$string .= join ('|', @{$self->to_array});
$string .= ']';
return $string;
@@ -121,6 +125,7 @@
return (0,0);
};
+
# Sort spans, attributes and relations
sub _sort {
@@ -135,64 +140,61 @@
my ($a_id) = ($a->[0] =~ m/^<s>(\d+)/);
my ($b_id) = ($b->[0] =~ m/^<s>(\d+)/);
if ($a_id > $b_id) {
- return 1;
+ return 1;
}
elsif ($a_id < $b_id) {
- return -1;
+ return -1;
}
else {
- return 1;
+ return 1;
};
}
# Both are relations
elsif (
(index($a->[5],'<:') == 0 || index($a->[5],'>:') == 0) &&
- (index($b->[5], '<:') == 0 || index($b->[5],'>:') == 0)) {
+ (index($b->[5], '<:') == 0 || index($b->[5],'>:') == 0)) {
- my $a_end = ($a->pti < 34 ? $a->p_start : (
- ($a->pti == 35 ? ($a->[0] =~ /^(?:<i>\d+){4}<i>(\d+)</ && $1) :
- ($a->[0] =~ /^(?:<i>\d+){2}<i>(\d+)</ && $1)
- )
+ my $a_end = ($a->get_pti < 34 ? $a->get_p_start : (
+ ($a->get_pti == 35 ? ($a->[0] =~ /^(?:<i>\d+){4}<i>(\d+)</ && $1) :
+ ($a->[0] =~ /^(?:<i>\d+){2}<i>(\d+)</ && $1)
+ )
));
- my $b_end = ($b->pti < 34 ? $b->p_start : (
- ($b->pti == 35 ? ($b->[0] =~ /^(?:<i>\d+){4}<i>(\d+)</ && $1) :
- ($b->[0] =~ /^(?:<i>\d+){2}<i>(\d+)</ && $1)
- )
+ my $b_end = ($b->get_pti < 34 ? $b->get_p_start : (
+ ($b->get_pti == 35 ? ($b->[0] =~ /^(?:<i>\d+){4}<i>(\d+)</ && $1) :
+ ($b->[0] =~ /^(?:<i>\d+){2}<i>(\d+)</ && $1)
+ )
));
-# my $a_end = $a->[2] // 0;
-# my $b_end = $b->[2] // 0;
-
# left is p_end
if ($a_end < $b_end) {
- return -1;
+ return -1;
}
elsif ($a_end > $b_end) {
- return 1;
+ return 1;
}
else {
- # Both are either > or <
+ # Both are either > or <
- # Check for right positions
- (my $a_start, $a_end) = _rel_right_pos($a->pti, $a->[0]);
- (my $b_start, $b_end) = _rel_right_pos($b->pti, $b->[0]);
- if ($a_start < $b_start) {
- return -1;
- }
- elsif ($a_start > $b_start) {
- return 1;
- }
- elsif ($a_end < $b_end) {
- return -1;
- }
- elsif ($a_end > $b_end) {
- return 1;
- }
- else {
- return 1;
- };
+ # Check for right positions
+ (my $a_start, $a_end) = _rel_right_pos($a->get_pti, $a->[0]);
+ (my $b_start, $b_end) = _rel_right_pos($b->get_pti, $b->[0]);
+ if ($a_start < $b_start) {
+ return -1;
+ }
+ elsif ($a_start > $b_start) {
+ return 1;
+ }
+ elsif ($a_end < $b_end) {
+ return -1;
+ }
+ elsif ($a_end > $b_end) {
+ return 1;
+ }
+ else {
+ return 1;
+ };
};
};
@@ -226,54 +228,20 @@
$a_depth //= 0;
$b_depth //= 0;
if ($a_depth < $b_depth) {
- return -1;
+ return -1;
}
elsif ($a_depth > $b_depth) {
- return 1;
+ return 1;
}
else {
- return $a->[5] cmp $b->[5];
+ return $a->[5] cmp $b->[5];
};
};
};
};
-sub to_solr {
- my $self = shift;
- my @array = map { $_->to_solr(0) } @{$self->{mt}};
- $array[0]->{i} = 1;
- return \@array;
-};
-
-
1;
__END__
-
-[
- {
- "e":128,
- "i":22,
- "p":"DQ4KDQsODg8=",
- "s":123,
- "t":"one",
- "y":"word"
- },
- {
- "e":8,
- "i":1,
- "s":5,
- "t":"two",
- "y":"word"
- },
- {
- "e":22,
- "i":1,
- "s":20,
- "t":"three",
- "y":"foobar"
- }
- ]
-
diff --git a/lib/KorAP/XML/Index/MultiTermTokenStream.pm b/lib/KorAP/XML/Index/MultiTermTokenStream.pm
index 7824ae3..1b7bfa2 100644
--- a/lib/KorAP/XML/Index/MultiTermTokenStream.pm
+++ b/lib/KorAP/XML/Index/MultiTermTokenStream.pm
@@ -1,15 +1,21 @@
package KorAP::XML::Index::MultiTermTokenStream;
-use Mojo::Base -base;
+use strict;
+use warnings;
use KorAP::XML::Index::MultiTermToken;
-has [qw/oStart oEnd/];
+use constant {
+ MTT => 0,
+ TUI => 1
+};
+
+sub new {
+ bless [[],[]], shift;
+};
sub add {
my $self = shift;
my $mtt = shift // KorAP::XML::Index::MultiTermToken->new;
- $self->{mtt} //= [];
- $self->{tui} //= [];
- push(@{$self->{mtt}}, $mtt);
+ push(@{$self->[MTT]}, $mtt);
return $mtt;
};
@@ -62,41 +68,36 @@
my $self = shift;
my $pos_0 = $self->pos(0) or return;
my $mt = $pos_0->add('-:' . shift);
- $mt->payload(shift);
- $mt->store_offsets(0);
+ $mt->set_payload(shift);
+ $mt->set_stored_offsets(0);
};
sub pos {
my $self = shift;
my $pos = shift;
return unless defined $pos;
- return $self->{mtt}->[$pos];
+ return $self->[MTT]->[$pos];
};
sub to_string {
my $self = shift;
- return join("\n" , map { $_->to_string } @{$self->{mtt}}) . "\n";
+ return join("\n" , map { $_->to_string } @{$self->[MTT]}) . "\n";
};
sub multi_term_tokens {
- $_[0]->{mtt};
+ $_[0]->[MTT];
};
sub tui {
my $self = shift;
my $pos = shift;
return unless defined $pos;
- return ++$self->{tui}->[$pos];
+ return ++$self->[TUI]->[$pos];
};
sub to_array {
my $self = shift;
- [ map { $_->to_array } @{$self->{mtt}} ];
-};
-
-sub to_solr {
- my $self = shift;
- [ map { $_->to_solr } @{$self->{mtt}} ];
+ [ map { $_->to_array } @{$self->[MTT]} ];
};
1;
diff --git a/lib/KorAP/XML/Tokenizer.pm b/lib/KorAP/XML/Tokenizer.pm
index 59ae17f..65daa94 100644
--- a/lib/KorAP/XML/Tokenizer.pm
+++ b/lib/KorAP/XML/Tokenizer.pm
@@ -178,8 +178,8 @@
$mtt->add('i:' . fc $token);
# Add offset information
- $mtt->o_start($from);
- $mtt->o_end($to);
+ $mtt->set_o_start($from);
+ $mtt->set_o_end($to);
# Store offset information for position matching
$range->set($from, $to, $have);
@@ -190,8 +190,8 @@
# Add position term
$mtt->add(
term => '_' . $have,
- o_start => $mtt->o_start,
- o_end => $mtt->o_end
+ o_start => $mtt->get_o_start,
+ o_end => $mtt->get_o_end
);
$have++;
diff --git a/lib/KorAP/XML/Tokenizer/Span.pm b/lib/KorAP/XML/Tokenizer/Span.pm
index 7d7bd55..962d002 100644
--- a/lib/KorAP/XML/Tokenizer/Span.pm
+++ b/lib/KorAP/XML/Tokenizer/Span.pm
@@ -19,6 +19,10 @@
$_[0]->[0];
};
+sub set_o_start {
+ $_[0]->[0] = $_[1];
+};
+
sub o_end {
if (defined $_[1]) {
$_[0]->[1] = $_[1];
@@ -26,6 +30,10 @@
$_[0]->[1];
};
+sub set_o_end {
+ $_[0]->[1] = $_[1];
+};
+
sub p_start {
if (defined $_[1]) {
$_[0]->[2] = $_[1];
@@ -33,6 +41,10 @@
$_[0]->[2];
};
+sub set_p_start {
+ $_[0]->[2] = $_[1];
+};
+
sub p_end {
if (defined $_[1]) {
$_[0]->[3] = $_[1];
@@ -40,6 +52,10 @@
$_[0]->[3];
};
+sub set_p_end {
+ $_[0]->[3] = $_[1];
+};
+
sub id {
if (defined $_[1]) {
$_[0]->[4] = $_[1];
diff --git a/lib/KorAP/XML/Tokenizer/Units.pm b/lib/KorAP/XML/Tokenizer/Units.pm
index 3ace9eb..7d31626 100644
--- a/lib/KorAP/XML/Tokenizer/Units.pm
+++ b/lib/KorAP/XML/Tokenizer/Units.pm
@@ -83,7 +83,7 @@
# The next token of end has a character
# offset AFTER the given end character offset
- my $real_start = $self->stream->pos($end)->o_start;
+ my $real_start = $self->stream->pos($end)->get_o_start;
# Ignore non-milestone elements outside the token stream!
if ($to <= $real_start) {
diff --git a/t/real/sgbr/script_single.t b/t/real/sgbr/script_single.t
index 934ce8a..553560a 100644
--- a/t/real/sgbr/script_single.t
+++ b/t/real/sgbr/script_single.t
@@ -17,9 +17,9 @@
};
my $f = dirname(__FILE__);
-my $script = catfile($f, '..', '..', 'script', 'korapxml2krill');
+my $script = catfile($f, '..', '..', '..', 'script', 'korapxml2krill');
-my $input = catdir($f, '..', 'sgbr', 'PRO-DUD', 'BSP-2013-01', '32');
+my $input = catdir($f, 'PRO-DUD', 'BSP-2013-01', '32');
my $output = tmpnam();
my $cache = tmpnam();
diff --git a/t/sort_tokens.t b/t/sort_tokens.t
index b5683d5..0db2c59 100644
--- a/t/sort_tokens.t
+++ b/t/sort_tokens.t
@@ -9,8 +9,8 @@
use_ok('KorAP::XML::Index::MultiTermTokenStream');
ok(my $mtt = KorAP::XML::Index::MultiTermToken->new, 'New token');
-ok(defined $mtt->o_start(0), 'Set start character offset');
-ok($mtt->o_end(5), 'Set end character offset');
+ok(defined $mtt->set_o_start(0), 'Set start character offset');
+ok($mtt->set_o_end(5), 'Set end character offset');
ok($mtt->add(term => '@:k=N',
pti => 128,
payload =>'<s>9'), 'Add token');
@@ -71,8 +71,8 @@
'Check string');
ok($mtt = KorAP::XML::Index::MultiTermToken->new, 'New token');
-ok(defined $mtt->o_start(0), 'Set start character offset');
-ok($mtt->o_end(5), 'Set end character offset');
+ok(defined $mtt->set_o_start(0), 'Set start character offset');
+ok($mtt->set_o_end(5), 'Set end character offset');
# 2-7 to 2-4
ok($mtt->add(term => '<:child-of',
diff --git a/t/tokens.t b/t/tokens.t
index ce083dd..9ea5bcd 100644
--- a/t/tokens.t
+++ b/t/tokens.t
@@ -16,36 +16,36 @@
o_end => 120
), 'Create new object');
-is($term->term, 'Baum');
-is($term->p_start, 0);
-is($term->p_end, 56);
-is($term->o_start, 34);
-is($term->o_end, 120);
-is($term->payload, '<i>56');
+is($term->get_term, 'Baum');
+is($term->get_p_start, 0);
+is($term->get_p_end, 56);
+is($term->get_o_start, 34);
+is($term->get_o_end, 120);
+is($term->get_payload, '<i>56');
is($term->to_string, 'Baum$<i>34<i>120<i>56<i>56');
ok($term = KorAP::XML::Index::MultiTerm->new(
term => 'Baum'
), 'Create new object');
-is($term->term, 'Baum');
-is($term->p_start, 0);
-is($term->p_end, 0);
-is($term->o_start, 0);
-is($term->o_end, 0);
-is($term->payload, undef);
+is($term->get_term, 'Baum');
+is($term->get_p_start, 0);
+is($term->get_p_end, 0);
+is($term->get_o_start, 0);
+is($term->get_o_end, 0);
+is($term->get_payload, undef);
is($term->to_string, 'Baum');
ok($term = KorAP::XML::Index::MultiTerm->new(
term => 'Ba#um'
), 'Create new object');
-is($term->term, 'Ba#um');
-is($term->p_start, 0);
-is($term->p_end, 0);
-is($term->o_start, 0);
-is($term->o_end, 0);
-is($term->payload, undef);
+is($term->get_term, 'Ba#um');
+is($term->get_p_start, 0);
+is($term->get_p_end, 0);
+is($term->get_o_start, 0);
+is($term->get_o_end, 0);
+is($term->get_payload, undef);
is($term->to_string, 'Ba\#um');
ok($term = KorAP::XML::Index::MultiTerm->new(
@@ -53,12 +53,12 @@
payload => '<i>45'
), 'Create new object');
-is($term->term, 'Ba#u$m');
-is($term->p_start, 0);
-is($term->p_end, 0);
-is($term->o_start, 0);
-is($term->o_end, 0);
-is($term->payload, '<i>45');
+is($term->get_term, 'Ba#u$m');
+is($term->get_p_start, 0);
+is($term->get_p_end, 0);
+is($term->get_o_start, 0);
+is($term->get_o_end, 0);
+is($term->get_payload, '<i>45');
is($term->to_string, 'Ba\#u\$m$<i>45');
use_ok('KorAP::XML::Tokenizer');
diff --git a/xt/benchmark.pl b/xt/benchmark.pl
index 69fc908..f481a83 100644
--- a/xt/benchmark.pl
+++ b/xt/benchmark.pl
@@ -73,7 +73,7 @@
}
),
Dumbbench::Instance::PerlSub->new(
- name => 'Conversion-GOE-Tagged-1',
+ name => 'Script-Conversion-GOE-Tagged-1',
code => sub {
my $doc = KorAP::XML::Krill->new(path => $path . '/');
$doc->parse;