Added struct support and PTI
Change-Id: Ia418958e1c26f2c83026c29089be806cad157762
diff --git a/t/index/corpus/doc/header.xml b/t/index/corpus/doc/header.xml
new file mode 100644
index 0000000..7a73824
--- /dev/null
+++ b/t/index/corpus/doc/header.xml
@@ -0,0 +1,41 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="header.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<!DOCTYPE idsCorpus PUBLIC "-//IDS//DTD IDS-XCES 1.0//EN" "http://corpora.ids-mannheim.de/idsxces1/DTD/ids.xcesdoc.dtd">
+<idsHeader type="document" pattern="text" status="new" version="1.1" TEIform="teiHeader">
+ <fileDesc>
+ <titleStmt>
+ <dokumentSigle>Corpus/Text</dokumentSigle>
+ <d.title>Beispiel Dokument</d.title>
+ </titleStmt>
+ <publicationStmt>
+ <distributor/>
+ <pubAddress/>
+ <availability region="world">QAO-NC</availability>
+ <pubDate/>
+ </publicationStmt>
+ <sourceDesc>
+ <biblStruct>
+ <monogr>
+ <h.title type="main"/>
+ <edition>
+ <further/>
+ <kind/>
+ <appearance/>
+ </edition>
+ <imprint/>
+ </monogr>
+ </biblStruct>
+ </sourceDesc>
+ </fileDesc>
+ <profileDesc>
+ <creation>
+ <creatDate>1827-1842</creatDate>
+ <creatRef>(Erstveröffentlichung: Stuttgart ; Tübingen, 1827-1842)</creatRef>
+ <creatRefShort>(Erstv. 1827-1842)</creatRefShort>
+ </creation>
+ <textDesc>
+ <textType>Aphorismus</textType>
+ <textTypeRef>Aphorismen</textTypeRef>
+ </textDesc>
+ </profileDesc>
+</idsHeader>
diff --git a/t/index/corpus/doc/text/base/paragraph.xml b/t/index/corpus/doc/text/base/paragraph.xml
new file mode 100644
index 0000000..be19d62
--- /dev/null
+++ b/t/index/corpus/doc/text/base/paragraph.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="span.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+
+<layer docid="ART_00001" xmlns="http://ids-mannheim.de/ns/KorAP" version="KorAP-0.4">
+ <spanList>
+ <span from="0" to="129" />
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/base/sentences.xml b/t/index/corpus/doc/text/base/sentences.xml
new file mode 100644
index 0000000..be19d62
--- /dev/null
+++ b/t/index/corpus/doc/text/base/sentences.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="span.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+
+<layer docid="ART_00001" xmlns="http://ids-mannheim.de/ns/KorAP" version="KorAP-0.4">
+ <spanList>
+ <span from="0" to="129" />
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/data.xml b/t/index/corpus/doc/text/data.xml
new file mode 100644
index 0000000..6b5af0f
--- /dev/null
+++ b/t/index/corpus/doc/text/data.xml
@@ -0,0 +1,7 @@
+<?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 docid="ART_ABC.00001" xmlns="http://ids-mannheim.de/ns/KorAP">
+ <metadata file="metadata.xml" />
+ <text>Zum letzten kulturellen Anlass lädt die Leitung des Schulheimes Hofbergli ein, bevor der Betrieb Ende Schuljahr eingestellt wird.</text>
+</raw_text>
diff --git a/t/index/corpus/doc/text/header.xml b/t/index/corpus/doc/text/header.xml
new file mode 100644
index 0000000..fb770f7
--- /dev/null
+++ b/t/index/corpus/doc/text/header.xml
@@ -0,0 +1,66 @@
+<?xml version="1.0" encoding="iso-8859-1"?>
+<?xml-model href="header.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<!DOCTYPE idsCorpus PUBLIC "-//IDS//DTD IDS-XCES 1.0//EN" "http://corpora.ids-mannheim.de/idsxces1/DTD/ids.xcesdoc.dtd">
+<idsHeader type="text" pattern="text" status="new" version="1.1" TEIform="teiHeader">
+ <fileDesc>
+ <titleStmt>
+ <textSigle>Corpus/Doc.Text</textSigle>
+ <t.title assemblage="regular"/>
+ </titleStmt>
+ <publicationStmt>
+ <distributor/>
+ <pubAddress/>
+ <availability region="world" status="unknown"/>
+ <pubDate/>
+ </publicationStmt>
+ <sourceDesc>
+ <biblStruct>
+ <analytic>
+ <h.title type="main">Beispiel Text</h.title>
+ <h.title type="sub">Beispiel Text Untertitel</h.title>
+ <h.author>Mustermann, Max</h.author>
+ <editor>Monkika Mustermann</editor>
+ <imprint/>
+ <biblScope type="pp"/>
+ <biblScope type="suppl"/>
+ <biblScope type="suppltitle"/>
+ <biblNote n="1"/>
+ </analytic>
+ <monogr>
+ <h.title type="main">Beispiel Text</h.title>
+ <h.title type="sub">Best of!</h.title>
+ <h.author>Mustermann, Max</h.author>
+ <editor>Monika Mustermann</editor>
+ <imprint>
+ <publisher>Artificial articles Inc.</publisher>
+ <pubDate type="year">2001</pubDate>
+ <pubDate type="month">04</pubDate>
+ <pubDate type="day">02</pubDate>
+ <pubPlace>Mannheim</pubPlace>
+ </imprint>
+ <biblScope type="issue"/>
+ <biblScope type="issueplace"/>
+ </monogr>
+ </biblStruct>
+ <reference type="complete" assemblage="regular"/>
+ <reference type="short" assemblage="regular"/>
+ </sourceDesc>
+ </fileDesc>
+ <profileDesc>
+ <creation>
+ <creatDate>1999.06.01</creatDate>
+ </creation>
+ <textClass>
+ <catRef n="1" target="topic.freizeit-unterhaltung.vereine-veranstaltungen" scheme="topic"/>
+ <h.keywords>
+ <keyTerm/>
+ </h.keywords>
+ </textClass>
+ <textDesc>
+ <textType>Zeitung: Tageszeitung</textType>
+ <textTypeArt>Bericht</textTypeArt>
+ <textDomain/>
+ <column/>
+ </textDesc>
+ </profileDesc>
+</idsHeader>
diff --git a/t/index/corpus/doc/text/opennlp/tokens.xml b/t/index/corpus/doc/text/opennlp/tokens.xml
new file mode 100644
index 0000000..b181a49
--- /dev/null
+++ b/t/index/corpus/doc/text/opennlp/tokens.xml
@@ -0,0 +1,24 @@
+<?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="ART_00001" VERSION="KorAP-0.4">
+<spanList>
+ <span id="s_7" from="0" to="3"/>
+ <span id="s_8" from="4" to="11"/>
+ <span id="s_9" from="12" to="23"/>
+ <span id="s_10" from="24" to="30"/>
+ <span id="s_11" from="31" to="35"/>
+ <span id="s_12" from="36" to="39"/>
+ <span id="s_13" from="40" to="47"/>
+ <span id="s_14" from="48" to="51"/>
+ <span id="s_15" from="52" to="63"/>
+ <span id="s_16" from="64" to="73"/>
+ <span id="s_17" from="74" to="77"/>
+ <span id="s_18" from="77" to="78"/>
+ <span id="s_19" from="79" to="84"/>
+ <span id="s_20" from="85" to="88"/>
+ <span id="s_21" from="89" to="96"/>
+ <span id="s_22" from="97" to="101"/>
+ <span id="s_23" from="102" to="111"/>
+ <span id="s_24" from="112" to="123"/>
+ <span id="s_25" from="124" to="128"/>
+ <span id="s_26" from="128" to="129"/>
+ </spanList>
+</layer>