Add support for NKJP
Change-Id: I264813c45b0ae8b5daed9d3c380ac33b6a7a54a1
diff --git a/lib/KorAP/XML/Annotation/NKJP/Morpho.pm b/lib/KorAP/XML/Annotation/NKJP/Morpho.pm
new file mode 100644
index 0000000..7150872
--- /dev/null
+++ b/lib/KorAP/XML/Annotation/NKJP/Morpho.pm
@@ -0,0 +1,50 @@
+package KorAP::XML::Annotation::NKJP::Morpho;
+use KorAP::XML::Annotation::Base;
+
+sub parse {
+ my $self = shift;
+
+ $$self->add_tokendata(
+ foundry => 'nkjp',
+ layer => 'morpho',
+ cb => sub {
+ my ($stream, $token) = @_;
+ my $mtt = $stream->pos($token->get_pos);
+
+ my $content = $token->get_hash->{fs}->{f};
+
+ my $found;
+
+ my $name;
+ foreach my $f (@{$content->{fs}->{f}}) {
+
+ $name = $f->{-name};
+
+ # pos tag
+ if (($name eq 'pos') &&
+ ($found = $f->{'#text'})) {
+ $mtt->add_by_term('nkjp/p:' . $found);
+ }
+
+ # lemma tag
+ elsif (($name eq 'lemma')
+ && ($found = $f->{'#text'})
+ && $found ne '<unknown>') {
+ $mtt->add_by_term('nkjp/l:' . $found);
+ }
+
+ # msd tag
+ elsif (($name eq 'msd')
+ && ($found = $f->{'#text'})) {
+ $mtt->add_by_term('nkjp/m:' . $found);
+ };
+ };
+ }) or return;
+ return 1;
+};
+
+sub layer_info {
+ ['nkjp/l=tokens', 'nkjp/p=tokens', 'nkjp/m=tokens']
+}
+
+1;
diff --git a/script/korapxml2krill b/script/korapxml2krill
index 5ed2af1..9c652ec 100644
--- a/script/korapxml2krill
+++ b/script/korapxml2krill
@@ -474,6 +474,10 @@
push(@layers,
['MDParser', 'Dependency']);
+# NKJP
+push(@layers,
+ ['NKJP', 'Morpho']);
+
# OpenNLP
push(@layers,
['OpenNLP', 'Morpho'],
diff --git a/t/real/corpus/NKJP/NKJP/KOT/data.xml b/t/real/corpus/NKJP/NKJP/KOT/data.xml
new file mode 100644
index 0000000..5727c58
--- /dev/null
+++ b/t/real/corpus/NKJP/NKJP/KOT/data.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="text.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<raw_text xmlns="http://ids-mannheim.de/ns/KorAP" docid="NKJP_NKJP.KOT">
+ <metadata file="metadata.xml"/>
+ <text>Nie zdążyłam jeszcze doprowadzić mieszkania do ładu po rządach Mini, która zrobiła w nim maksi bałagan, kiedy na horyzoncie za sprawą pani Joasi pojawił się czarny jak smoła Dratewka. Dratewkę pani Joasia wyrwała z bestialskich łap pewnego szewca, którego niech piekło pochłonie.</text>
+</raw_text>
diff --git a/t/real/corpus/NKJP/NKJP/KOT/header.xml b/t/real/corpus/NKJP/NKJP/KOT/header.xml
new file mode 100644
index 0000000..f2f29bc
--- /dev/null
+++ b/t/real/corpus/NKJP/NKJP/KOT/header.xml
@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<idsHeader type="document"
+ pattern="text"
+ status="new"
+ version="1.1"
+ TEIform="teiHeader">
+ <fileDesc>
+ <titleStmt>
+ <textSigle>NKJP/NKJP.KOT</textSigle>
+ <t.title>TEI P5 encoded version of sample(s) of "Kot"</t.title>
+ </titleStmt>
+ <publicationStmt>
+ <availability status="free">
+ <p>See the licence agreement.</p>
+ </availability>
+ </publicationStmt>
+ </fileDesc>
+ <profileDesc>
+ <textClass>
+ <catRef scheme="#taxonomy-NKJP-type" target="#typ_publ"/>
+ <catRef scheme="#taxonomy-NKJP-channel" target="#kanal_prasa_miesiecznik"/>
+ </textClass>
+ </profileDesc>
+</idsHeader>
diff --git a/t/real/corpus/NKJP/NKJP/KOT/nkjp/morpho.xml b/t/real/corpus/NKJP/NKJP/KOT/nkjp/morpho.xml
new file mode 100644
index 0000000..5bcbb7c
--- /dev/null
+++ b/t/real/corpus/NKJP/NKJP/KOT/nkjp/morpho.xml
@@ -0,0 +1,532 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="span.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<layer xmlns="http://ids-mannheim.de/ns/KorAP"
+ docid="NKJP_NKJP.KOT"
+ version="KorAP-0.4">
+ <spanList>
+ <span id="s6" from="0" to="3" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Nie-->
+ <f name="lemma">nie</f>
+ <f name="pos">qub</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s7" from="4" to="11" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--zdążyła-->
+ <f name="lemma">zdążyć</f>
+ <f name="pos">praet</f>
+ <f name="msd">sg:f:perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s8" from="11" to="12" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--m-->
+ <f name="lemma">być</f>
+ <f name="pos">aglt</f>
+ <f name="msd">sg:pri:imperf:nwok</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s9" from="13" to="20" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--jeszcze-->
+ <f name="lemma">jeszcze</f>
+ <f name="pos">qub</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s10" from="21" to="32" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--doprowadzić-->
+ <f name="lemma">doprowadzić</f>
+ <f name="pos">inf</f>
+ <f name="msd">perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s11" from="33" to="43" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--mieszkania-->
+ <f name="lemma">mieszkanie</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:n</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s12" from="44" to="46" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--do-->
+ <f name="lemma">do</f>
+ <f name="pos">prep</f>
+ <f name="msd">gen</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s13" from="47" to="51" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--ładu-->
+ <f name="lemma">ład</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:m3</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s14" from="52" to="54" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--po-->
+ <f name="lemma">po</f>
+ <f name="pos">prep</f>
+ <f name="msd">loc</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s15" from="55" to="62" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--rządach-->
+ <f name="lemma">rząd</f>
+ <f name="pos">subst</f>
+ <f name="msd">pl:loc:m3</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s16" from="63" to="67" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Mini-->
+ <f name="lemma">Minia</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s17" from="67" to="68" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--,-->
+ <f name="lemma">,</f>
+ <f name="pos">interp</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s18" from="69" to="74" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--która-->
+ <f name="lemma">który</f>
+ <f name="pos">adj</f>
+ <f name="msd">sg:nom:f:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s19" from="75" to="82" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--zrobiła-->
+ <f name="lemma">zrobić</f>
+ <f name="pos">praet</f>
+ <f name="msd">sg:f:perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s20" from="83" to="84" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--w-->
+ <f name="lemma">w</f>
+ <f name="pos">prep</f>
+ <f name="msd">loc:nwok</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s21" from="85" to="88" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--nim-->
+ <f name="lemma">on</f>
+ <f name="pos">ppron3</f>
+ <f name="msd">sg:loc:n:ter:akc:praep</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s22" from="89" to="94" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--maksi-->
+ <f name="lemma">maksi</f>
+ <f name="pos">adj</f>
+ <f name="msd">sg:acc:m3:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s23" from="95" to="102" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--bałagan-->
+ <f name="lemma">bałagan</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:acc:m3</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s24" from="102" to="103" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--,-->
+ <f name="lemma">,</f>
+ <f name="pos">interp</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s25" from="104" to="109" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--kiedy-->
+ <f name="lemma">kiedy</f>
+ <f name="pos">adv</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s26" from="110" to="112" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--na-->
+ <f name="lemma">na</f>
+ <f name="pos">prep</f>
+ <f name="msd">loc</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s27" from="113" to="123" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--horyzoncie-->
+ <f name="lemma">horyzont</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:loc:m3</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s28" from="124" to="126" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--za-->
+ <f name="lemma">za</f>
+ <f name="pos">prep</f>
+ <f name="msd">inst</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s29" from="127" to="133" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--sprawą-->
+ <f name="lemma">sprawa</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:inst:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s30" from="134" to="138" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--pani-->
+ <f name="lemma">pani</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s31" from="139" to="144" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Joasi-->
+ <f name="lemma">Joasia</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s32" from="145" to="152" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--pojawił-->
+ <f name="lemma">pojawić</f>
+ <f name="pos">praet</f>
+ <f name="msd">sg:m2:perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s33" from="153" to="156" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--się-->
+ <f name="lemma">się</f>
+ <f name="pos">qub</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s34" from="157" to="163" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--czarny-->
+ <f name="lemma">czarny</f>
+ <f name="pos">adj</f>
+ <f name="msd">sg:nom:m2:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s35" from="164" to="167" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--jak-->
+ <f name="lemma">jak</f>
+ <f name="pos">prep</f>
+ <f name="msd">nom</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s36" from="168" to="173" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--smoła-->
+ <f name="lemma">smoła</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:nom:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s37" from="174" to="182" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Dratewka-->
+ <f name="lemma">Dratewka</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:nom:m2</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s38" from="182" to="183" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--.-->
+ <f name="lemma">.</f>
+ <f name="pos">interp</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s40" from="184" to="192" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Dratewkę-->
+ <f name="lemma">Dratewka</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:acc:m2</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s41" from="193" to="197" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--pani-->
+ <f name="lemma">pani</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:nom:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s42" from="198" to="204" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--Joasia-->
+ <f name="lemma">Joasia</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:nom:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s43" from="205" to="212" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--wyrwała-->
+ <f name="lemma">wyrwać</f>
+ <f name="pos">praet</f>
+ <f name="msd">sg:f:perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s44" from="213" to="214" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--z-->
+ <f name="lemma">z</f>
+ <f name="pos">prep</f>
+ <f name="msd">gen:nwok</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s45" from="215" to="227" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--bestialskich-->
+ <f name="lemma">bestialski</f>
+ <f name="pos">adj</f>
+ <f name="msd">pl:gen:f:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s46" from="228" to="231" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--łap-->
+ <f name="lemma">łapa</f>
+ <f name="pos">subst</f>
+ <f name="msd">pl:gen:f</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s47" from="232" to="239" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--pewnego-->
+ <f name="lemma">pewien</f>
+ <f name="pos">adj</f>
+ <f name="msd">sg:gen:m1:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s48" from="240" to="246" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--szewca-->
+ <f name="lemma">szewc</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:gen:m1</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s49" from="246" to="247" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--,-->
+ <f name="lemma">,</f>
+ <f name="pos">interp</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s50" from="248" to="255" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--którego-->
+ <f name="lemma">który</f>
+ <f name="pos">adj</f>
+ <f name="msd">sg:acc:m1:pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s51" from="256" to="261" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--niech-->
+ <f name="lemma">niech</f>
+ <f name="pos">qub</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s52" from="262" to="268" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--piekło-->
+ <f name="lemma">piekło</f>
+ <f name="pos">subst</f>
+ <f name="msd">sg:nom:n</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s53" from="269" to="278" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--pochłonie-->
+ <f name="lemma">pochłonąć</f>
+ <f name="pos">fin</f>
+ <f name="msd">sg:ter:perf</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s54" from="278" to="279" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="lex">
+ <f name="lex">
+ <fs><!--.-->
+ <f name="lemma">.</f>
+ <f name="pos">interp</f>
+ <f name="join">left</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/real/corpus/NKJP/NKJP/KOT/struct/structure.xml b/t/real/corpus/NKJP/NKJP/KOT/struct/structure.xml
new file mode 100644
index 0000000..0d711ea
--- /dev/null
+++ b/t/real/corpus/NKJP/NKJP/KOT/struct/structure.xml
@@ -0,0 +1,786 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="span.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<layer xmlns="http://ids-mannheim.de/ns/KorAP"
+ docid="NKJP_NKJP.KOT"
+ version="KorAP-0.4">
+ <spanList>
+ <span id="s2" from="0" to="279" l="1">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">text</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="id">segm_text</f>
+ <f name="lang">pl</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s3" from="0" to="279" l="2">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">body</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="id">segm_body</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s4" from="0" to="279" l="3">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">p</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#txt_76-div</f>
+ <f name="id">segm_76-p</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s5" from="0" to="183" l="4">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="id">segm_76.33-s</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s6" from="0" to="3" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,0,3)</f>
+ <f name="id">segm_76.1-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s7" from="4" to="11" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,4,7)</f>
+ <f name="id">segm_76.2-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s8" from="11" to="12" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,11,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.3-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s9" from="13" to="20" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,13,7)</f>
+ <f name="id">segm_76.4-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s10" from="21" to="32" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,21,11)</f>
+ <f name="id">segm_76.5-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s11" from="33" to="43" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,33,10)</f>
+ <f name="id">segm_76.6-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s12" from="44" to="46" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,44,2)</f>
+ <f name="id">segm_76.7-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s13" from="47" to="51" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,47,4)</f>
+ <f name="id">segm_76.8-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s14" from="52" to="54" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,52,2)</f>
+ <f name="id">segm_76.9-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s15" from="55" to="62" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,55,7)</f>
+ <f name="id">segm_76.10-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s16" from="63" to="67" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,63,4)</f>
+ <f name="id">segm_76.11-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s17" from="67" to="68" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,67,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.12-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s18" from="69" to="74" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,69,5)</f>
+ <f name="id">segm_76.13-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s19" from="75" to="82" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,75,7)</f>
+ <f name="id">segm_76.14-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s20" from="83" to="84" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,83,1)</f>
+ <f name="id">segm_76.15-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s21" from="85" to="88" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,85,3)</f>
+ <f name="id">segm_76.16-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s22" from="89" to="94" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,89,5)</f>
+ <f name="id">segm_76.17-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s23" from="95" to="102" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,95,7)</f>
+ <f name="id">segm_76.18-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s24" from="102" to="103" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,102,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.19-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s25" from="104" to="109" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,104,5)</f>
+ <f name="id">segm_76.20-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s26" from="110" to="112" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,110,2)</f>
+ <f name="id">segm_76.21-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s27" from="113" to="123" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,113,10)</f>
+ <f name="id">segm_76.22-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s28" from="124" to="126" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,124,2)</f>
+ <f name="id">segm_76.23-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s29" from="127" to="133" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,127,6)</f>
+ <f name="id">segm_76.24-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s30" from="134" to="138" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,134,4)</f>
+ <f name="id">segm_76.25-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s31" from="139" to="144" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,139,5)</f>
+ <f name="id">segm_76.26-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s32" from="145" to="152" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,145,7)</f>
+ <f name="id">segm_76.27-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s33" from="153" to="156" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,153,3)</f>
+ <f name="id">segm_76.28-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s34" from="157" to="163" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,157,6)</f>
+ <f name="id">segm_76.29-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s35" from="164" to="167" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,164,3)</f>
+ <f name="id">segm_76.30-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s36" from="168" to="173" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,168,5)</f>
+ <f name="id">segm_76.31-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s37" from="174" to="182" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,174,8)</f>
+ <f name="id">segm_76.32-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s38" from="182" to="183" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,182,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.33-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s39" from="184" to="279" l="4">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="id">segm_76.48-s</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s40" from="184" to="192" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,184,8)</f>
+ <f name="id">segm_76.34-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s41" from="193" to="197" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,193,4)</f>
+ <f name="id">segm_76.35-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s42" from="198" to="204" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,198,6)</f>
+ <f name="id">segm_76.36-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s43" from="205" to="212" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,205,7)</f>
+ <f name="id">segm_76.37-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s44" from="213" to="214" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,213,1)</f>
+ <f name="id">segm_76.38-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s45" from="215" to="227" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,215,12)</f>
+ <f name="id">segm_76.39-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s46" from="228" to="231" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,228,3)</f>
+ <f name="id">segm_76.40-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s47" from="232" to="239" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,232,7)</f>
+ <f name="id">segm_76.41-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s48" from="240" to="246" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,240,6)</f>
+ <f name="id">segm_76.42-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s49" from="246" to="247" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,246,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.43-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s50" from="248" to="255" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,248,7)</f>
+ <f name="id">segm_76.44-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s51" from="256" to="261" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,256,5)</f>
+ <f name="id">segm_76.45-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s52" from="262" to="268" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,262,6)</f>
+ <f name="id">segm_76.46-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s53" from="269" to="278" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,269,9)</f>
+ <f name="id">segm_76.47-seg</f>
+ <f name="nps">false</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s54" from="278" to="279" l="5">
+ <fs xmlns="http://www.tei-c.org/ns/1.0" type="struct">
+ <f name="name">seg</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="corresp">text.xml#string-range(txt_76.1-ab,278,1)</f>
+ <f name="nps">true</f>
+ <f name="id">segm_76.48-seg</f>
+ <f name="rejected">false</f>
+ <f name="part">N</f>
+ <f name="type">token</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/real/corpus/NKJP/header.xml b/t/real/corpus/NKJP/header.xml
new file mode 100644
index 0000000..da2df68
--- /dev/null
+++ b/t/real/corpus/NKJP/header.xml
@@ -0,0 +1,131 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<idsHeader type="corpus"
+ pattern="text"
+ status="new"
+ version="1.1"
+ TEIform="teiHeader">
+ <fileDesc>
+ <titleStmt>
+ <korpusSigle>NKJP</korpusSigle>
+ <c.title xml:lang="pl">Narodowy Korpus Języka Polskiego -- podkorpus zawierający 1 milion słów</c.title>
+ <c.title xml:lang="en">National Corpus of Polish -- the 1 million word subcorpus</c.title>
+ </titleStmt>
+ <publicationStmt>
+ <availability status="unknown">
+ <p>This 1 million word subcorpus of the National Corpus of Polish is available publicly for free.</p>
+ </availability>
+ </publicationStmt>
+ </fileDesc>
+ <encodingDesc>
+ <classDecl>
+ <taxonomy xml:id="taxonomy-NKJP-type">
+ <category xml:id="typ_lit">
+ <desc xml:lang="pl">literatura piękna</desc>
+ <desc xml:lang="en">fiction</desc>
+ </category>
+ <category xml:id="typ_fakt">
+ <desc xml:lang="pl">literatura faktu</desc>
+ <desc xml:lang="en">non-fiction novel</desc>
+ </category>
+ <category xml:id="typ_publ">
+ <desc xml:lang="pl">publicystyka i wiadomości prasowe</desc>
+ <desc xml:lang="en">journalism</desc>
+ </category>
+ <category xml:id="typ_nd">
+ <desc xml:lang="pl">naukowo-dydaktyczny</desc>
+ <desc xml:lang="en">academic writing</desc>
+ </category>
+ <category xml:id="typ_inf-por">
+ <desc xml:lang="pl">informacyjno-poradnikowy</desc>
+ <desc xml:lang="en">informative and instructive writing</desc>
+ </category>
+ <category xml:id="typ_nklas">
+ <desc xml:lang="pl">książka niebeletrystyczna niesklasyfikowana</desc>
+ <desc xml:lang="en">unclassified non-fiction book</desc>
+ </category>
+ <category xml:id="typ_inne_pisane">
+ <desc xml:lang="pl">inne teksty pisane</desc>
+ <desc xml:lang="en">miscellaneous (written)</desc>
+ <category xml:id="typ_urzed">
+ <desc xml:lang="pl">urzędowo-kancelaryjny</desc>
+ <desc xml:lang="en">legal and official</desc>
+ </category>
+ </category>
+ <category xml:id="typ_internet">
+ <desc xml:lang="pl">Internet</desc>
+ <desc xml:lang="en">Internet</desc>
+ </category>
+ <category xml:id="typ_konwers">
+ <desc xml:lang="pl">konwersacyjne</desc>
+ <desc xml:lang="en">conversational</desc>
+ </category>
+ <category xml:id="typ_media">
+ <desc xml:lang="pl">mówione medialne</desc>
+ <desc xml:lang="en">spoken from the media</desc>
+ </category>
+ <category xml:id="typ_qmow">
+ <desc xml:lang="pl">quasi-mówione</desc>
+ <desc xml:lang="en">quasi-spoken</desc>
+ </category>
+ </taxonomy>
+ </classDecl>
+ <classDecl>
+ <taxonomy xml:id="taxonomy-NKJP-channel">
+ <category xml:id="kanal_prasa">
+ <desc xml:lang="pl">prasa</desc>
+ <desc xml:lang="en">press</desc>
+ <category xml:id="kanal_prasa_dziennik">
+ <desc xml:lang="pl">dziennik</desc>
+ <desc xml:lang="en">daily</desc>
+ </category>
+ <category xml:id="kanal_prasa_tygodnik">
+ <desc xml:lang="pl">tygodnik</desc>
+ <desc xml:lang="en">weekly</desc>
+ </category>
+ <category xml:id="kanal_prasa_miesiecznik">
+ <desc xml:lang="pl">miesiecznik</desc>
+ <desc xml:lang="en">monthly</desc>
+ </category>
+ <category xml:id="kanal_prasa_inne">
+ <desc xml:lang="pl">inne prasowe</desc>
+ <desc xml:lang="en">other press</desc>
+ </category>
+ </category>
+ <category xml:id="kanal_ksiazka">
+ <desc xml:lang="pl">książka</desc>
+ <desc xml:lang="en">book</desc>
+ </category>
+ <category xml:id="kanal_internet">
+ <desc xml:lang="pl">Internet</desc>
+ <desc xml:lang="en">internet</desc>
+ </category>
+ <category xml:id="kanal_mowiony">
+ <desc xml:lang="pl">mówiony</desc>
+ <desc xml:lang="en">spoken</desc>
+ </category>
+ <category xml:id="kanal_ulotka">
+ <desc xml:lang="pl">ulotki, ogłoszenia, reklamy</desc>
+ <desc xml:lang="en">leaflets, announcemnets, ads</desc>
+ </category>
+ </taxonomy>
+ </classDecl>
+ <classDecl>
+ <taxonomy xml:id="ukd">
+ <bibl>
+ <title xml:lang="pl">Uniwersalna Klasyfikacja Dziesiętna</title>
+ <title xml:lang="en">Universal Decimal Classification</title>
+ <edition>UDC-P058</edition>
+ </bibl>
+ </taxonomy>
+ </classDecl>
+ <classDecl>
+ <taxonomy xml:id="bn">
+ <bibl>
+ <title xml:lang="pl">Klasyfikacja Biblioteki Narodowej</title>
+ <title xml:lang="en">Polish National Library Classification</title>
+ <edition>Słownik języka haseł przedmiotowych Biblioteki Narodowej. Wyd. 5 popr. i rozsz., stan na dzień 31 grudnia 2004 roku.</edition>
+ </bibl>
+ </taxonomy>
+ </classDecl>
+ </encodingDesc>
+</idsHeader>
diff --git a/t/real/nkjp.t b/t/real/nkjp.t
new file mode 100644
index 0000000..dfc645b
--- /dev/null
+++ b/t/real/nkjp.t
@@ -0,0 +1,88 @@
+use strict;
+use warnings;
+use Test::More;
+use Data::Dumper;
+use JSON::XS;
+
+if ($ENV{SKIP_REAL}) {
+ plan skip_all => 'Skip real tests';
+};
+
+use utf8;
+use lib 'lib', '../lib';
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+use_ok('KorAP::XML::Krill');
+
+my $path = catdir(dirname(__FILE__), 'corpus','NKJP','NKJP','KOT');
+
+ok(my $doc = KorAP::XML::Krill->new( path => $path . '/' ), 'Load Korap::Document');
+ok($doc->parse, 'Parse document');
+
+is($doc->text_sigle, 'NKJP/NKJP/KOT', 'Correct text sigle');
+is($doc->doc_sigle, 'NKJP/NKJP', 'Correct document sigle');
+is($doc->corpus_sigle, 'NKJP', 'Correct corpus sigle');
+
+my $meta = $doc->meta;
+
+is($meta->{T_title}, 'TEI P5 encoded version of sample(s) of "Kot"', 'Title');
+ok(!$meta->{T_sub_title}, 'SubTitle');
+ok(!$meta->{T_author}, 'Author');
+ok(!$meta->{A_editor}, 'Editor');
+ok(!$meta->{S_pub_place}, 'PubPlace');
+ok(!$meta->{A_publisher}, 'Publisher');
+
+ok(!$meta->{S_text_type}, 'No Text Type');
+ok(!$meta->{S_text_type_art}, 'No Text Type Art');
+ok(!$meta->{S_text_type_ref}, 'No Text Type Ref');
+ok(!$meta->{S_text_domain}, 'No Text Domain');
+ok(!$meta->{S_text_column}, 'No Text Column');
+
+
+# Tokenization
+use_ok('KorAP::XML::Tokenizer');
+
+my ($token_base_foundry, $token_base_layer) = (qw/nkjp Morpho/);
+
+# Get tokenization
+my $tokens = KorAP::XML::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => $token_base_foundry,
+ layer => $token_base_layer,
+ name => 'tokens'
+);
+ok($tokens, 'Token Object is fine');
+ok($tokens->parse, 'Token parsing is fine');
+
+my $output = decode_json( $tokens->to_json );
+
+is($output->{data}->{stream}->[0]->[0], '-:tokens$<i>43', 't');
+is($output->{data}->{stream}->[0]->[3], 'i:nie', 't');
+is($output->{data}->{stream}->[1]->[2], 's:zdążyła', 't');
+
+## Base
+ok($tokens->add('DeReKo', 'Structure', 'base_sentences_paragraphs'));
+ok($tokens->add('NKJP', 'Morpho'), 'Add Gingko');
+
+$output = $tokens->to_data;
+
+is($output->{data}->{foundries}, 'dereko dereko/structure dereko/structure/base_sentences_paragraphs nkjp nkjp/morpho', 'Foundries');
+
+is($output->{data}->{layerInfos}, 'dereko/s=spans nkjp/l=tokens nkjp/m=tokens nkjp/p=tokens', 'layerInfos');
+
+my $token = join('||', @{$output->{data}->{stream}->[7]});
+
+like($token, qr!<>:dereko\/s:seg\$<b>64!);
+like($token, qr!<>:dereko\/s:seg\$<b>64!);
+like($token, qr!i:ładu!);
+like($token, qr!nkjp\/l:ład!);
+like($token, qr!nkjp\/m:sg:gen:m3!);
+like($token, qr!nkjp\/p:subst!);
+like($token, qr!s:ładu!);
+
+done_testing;
+__END__
+