Added mate morpho tests
Change-Id: I16ab6b777b0d9f1241b755e25f3e0682ce18baaa
diff --git a/D59-00089.json b/D59-00089.json
new file mode 100644
index 0000000..0fe3bfe
--- /dev/null
+++ b/D59-00089.json
@@ -0,0 +1 @@
+{"textType":"Zeitung: Tageszeitung","textColumn":"POLITIK","docSigle":"BZK_D59","reference":"Neues Deutschland, [Tageszeitung], 19.02.1959, Jg. 14, Berliner Ausgabe, S. 7. - Sachgebiet: Politik, Originalressort: POLITIK; Saragat-Partei zerfällt","pubPlace":"Berlin","textClass":"politik ausland","corpusTitle":"Bonner Zeitungskorpus","language":"de","version":"0.03","data":{"tokenSource":"opennlp#tokens","foundries":"base base/paragraphs base/sentences corenlp corenlp/constituency corenlp/morpho corenlp/namedentities corenlp/sentences glemm glemm/morpho mate mate/morpho opennlp opennlp/morpho opennlp/sentences treetagger treetagger/morpho treetagger/sentences","layerInfos":"base/s=spans corenlp/c=spans corenlp/ne=tokens corenlp/p=tokens corenlp/s=spans glemm/l=tokens mate/l=tokens mate/m=tokens mate/p=tokens opennlp/p=tokens opennlp/s=spans tt/l=tokens tt/p=tokens tt/s=spans","text":"Saragat-Partei zerfällt Rom (ADN) die von dem Rechtssozialisten Saragat geführte Sozialdemokratische Partei Italiens fällt immer mehr auseinander, nachdem vor einiger Zeit mehrere prominente Mitglieder ihren Austritt erklärt und unter dem Namen \"Einheitsbewegung der sozialistischen Initiative\" eine neue politische Gruppierung ins Leben gerufen hatten. Pressemeldungen zufolge haben sich in den letzten Tagen acht Provinzorganisationen der Sozialdemokratischen Partei der \"Einheitsbewegung\" angeschlossen. zu ihnen gehören die Organisation von Trient, Bozen und Triest. die Provinzorganisationen Treviso, Bergamo und Sondrio beschlossen mit überwältigender Mehrheit den Austritt aus der Saragat-Partei. von den 98 Jugendorganisationen der Sozialdemokratischen Partei haben sich inzwischen 90 der neuen \"Einheitsbewegung\" angeschlossen.","stream":[["-:base/paragraphs$<i>1","-:base/sentences$<i>7","-:corenlp/sentences$<i>5","-:opennlp/sentences$<i>5","-:tokens$<i>99","-:tt/sentences$<i>5","<>:base/s:s$<b>64<i>0<i>23<i>2<b>2","<>:corenlp/c:S$<b>64<i>0<i>29<i>3<b>2","<>:corenlp/c:ROOT$<b>64<i>0<i>353<i>43<b>0","<>:corenlp/s:s$<b>64<i>0<i>353<i>43<b>0","<>:opennlp/s:s$<b>64<i>0<i>353<i>43<b>0","<>:tt/s:s$<b>64<i>0<i>353<i>43<b>0","<>:corenlp/c:CS$<b>64<i>0<i>353<i>43<b>1","<>:base/s:t$<b>64<i>0<i>836<i>98<b>0","_0$<i>0<i>14","corenlp/p:NN","glemm/l:__Partei","glemm/l:__Saragat","i:saragat-partei","mate/l:saragat-partei","mate/m:case:nom","mate/m:gender:*","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Saragat-Partei","tt/p:NE$<b>129<b>28","tt/p:NN$<b>129<b>215"],["<>:corenlp/c:NP-SB$<b>64<i>20<i>23<i>2<b>3","_1$<i>15<i>23","glemm/l:_+fallen","glemm/l:_+fällen","glemm/l:_+zer-","glemm/l:__zerfallen","i:zerfällt","mate/l:zerfallen","mate/m:mood:ind","mate/m:number:sg","mate/m:person:3","mate/m:tense:pres","mate/p:VVFIN","opennlp/p:VVFIN","s:zerfällt","tt/l:zerfallen$<b>129<b>255","tt/p:VVFIN$<b>129<b>255"],["<>:corenlp/c:NP-OA$<b>64<i>24<i>29<i>3<b>3","<>:corenlp/c:MPN$<b>64<i>24<i>29<i>3<b>4","<>:base/s:s$<b>64<i>24<i>33<i>4<b>2","_2$<i>24<i>27","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Rom","i:rom","mate/l:rom","mate/m:case:acc","mate/m:gender:*","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Rom","tt/l:Rom$<b>129<b>255","tt/p:NE$<b>129<b>255"],["<>:corenlp/c:NP-OA$<b>64<i>29<i>33<i>4<b>3","<>:corenlp/c:MPN$<b>64<i>29<i>33<i>4<b>4","<>:corenlp/c:S$<b>64<i>29<i>118<i>13<b>2","_3$<i>29<i>32","corenlp/ne:I-ORG","corenlp/p:NE","glemm/l:__ADN","glemm/l:__Adn","i:adn","mate/l:adn","mate/p:NE","opennlp/p:NE","s:ADN","tt/l:ADN$<b>129<b>255","tt/p:NE$<b>129<b>255"],["<>:corenlp/c:NP-SB$<b>64<i>34<i>116<i>13<b>3","<>:base/s:s$<b>64<i>34<i>353<i>43<b>2","<>:base/s:p$<b>64<i>34<i>836<i>98<b>1","_4$<i>34<i>37","corenlp/p:ART","glemm/l:__d-","i:die","mate/l:der","mate/m:case:acc","mate/m:gender:fem","mate/m:number:pl","mate/p:ART","opennlp/p:ART","s:die","tt/l:die$<b>129<b>123","tt/l:die$<b>129<b>107","tt/l:die$<b>129<b>23","tt/p:ART$<b>129<b>107","tt/p:PDS$<b>129<b>23","tt/p:PRELS$<b>129<b>123"],["<>:corenlp/c:PP$<b>64<i>38<i>75<i>9<b>5","<>:corenlp/c:AP$<b>64<i>38<i>80<i>10<b>4","_5$<i>38<i>41","corenlp/p:APPR","glemm/l:__von","i:von","mate/l:von","mate/p:APPR","opennlp/p:APPR","s:von","tt/l:von$<b>129<b>254","tt/p:APPR$<b>129<b>254"],["_6$<i>42<i>45","corenlp/p:ART","glemm/l:__d-","i:dem","mate/l:der","mate/m:case:dat","mate/m:gender:neut","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:dem","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_7$<i>46<i>63","corenlp/p:NN","glemm/l:++-ist","glemm/l:++sozial","glemm/l:+_Recht","glemm/l:+_Sozialist","glemm/l:+_rechts","glemm/l:__Rechtssozialist","i:rechtssozialisten","mate/l:rechtssozialist","mate/m:case:dat","mate/m:degree:sup","mate/m:gender:neut","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Rechtssozialisten","tt/p:ADJA$<b>129<b>37","tt/p:NN$<b>129<b>210"],["<>:corenlp/c:MPN$<b>64<i>64<i>75<i>9<b>6","_8$<i>64<i>71","corenlp/p:NE","glemm/l:__Saragat","i:saragat","mate/l:saragat","mate/m:case:nom","mate/m:gender:*","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Saragat","tt/p:NE$<b>129<b>213","tt/p:NN$<b>129<b>41"],["_9$<i>72<i>80","glemm/l:_+führen","glemm/l:__geführt","i:geführte","mate/l:geführt","mate/m:case:acc","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:geführte","tt/l:geführt$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_10$<i>81<i>100","corenlp/ne:I-MISC","corenlp/p:ADJA","glemm/l:++Demokrat","glemm/l:+_demokratisch","glemm/l:+_sozial","glemm/l:_+-isch","glemm/l:_+Sozialdemokrat","glemm/l:__sozialdemokratisch","i:sozialdemokratische","mate/l:sozialdemokratisch","mate/m:case:acc","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:Sozialdemokratische","tt/l:Sozialdemokratische$<b>129<b>56","tt/l:sozialdemokratisch$<b>129<b>198","tt/p:ADJA$<b>129<b>198","tt/p:NN$<b>129<b>56"],["_11$<i>101<i>107","corenlp/p:NN","glemm/l:__Partei","i:partei","mate/l:partei","mate/m:case:acc","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Partei","tt/l:Partei$<b>129<b>255","tt/p:NN$<b>129<b>255"],["_12$<i>108<i>116","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Italien","i:italiens","mate/l:italien","mate/m:case:gen","mate/m:gender:neut","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Italiens","tt/l:Italien$<b>129<b>255","tt/p:NE$<b>129<b>255"],["<>:corenlp/c:S$<b>64<i>119<i>224<i>27<b>2","_13$<i>117<i>122","glemm/l:__fallen","glemm/l:__fällen","i:fällt","mate/l:fallen","mate/m:mood:ind","mate/m:number:sg","mate/m:person:3","mate/m:tense:pres","mate/p:VVFIN","opennlp/p:VVFIN","s:fällt","tt/l:fallen|fällen$<b>129<b>255","tt/p:VVFIN$<b>129<b>255"],["<>:corenlp/c:AVP$<b>64<i>123<i>133<i>16<b>3","_14$<i>123<i>128","corenlp/p:ADV","glemm/l:__immer","i:immer","mate/l:immer","mate/p:ADV","opennlp/p:ADV","s:immer","tt/l:immer$<b>129<b>255","tt/p:ADV$<b>129<b>255"],["_15$<i>129<i>133","corenlp/p:PIAT","glemm/l:__mehr","i:mehr","mate/l:mehr","mate/p:PIS","opennlp/p:PIAT","s:mehr","tt/l:mehr$<b>129<b>211","tt/l:mehr$<b>129<b>34","tt/p:ADV$<b>129<b>211","tt/p:PIAT$<b>129<b>34"],["_16$<i>134<i>145","corenlp/p:PTKVZ","glemm/l:__auseinander","i:auseinander","mate/l:auseinander","mate/p:PTKVZ","opennlp/p:PTKVZ","s:auseinander","tt/l:auseinander$<b>129<b>249","tt/p:PTKVZ$<b>129<b>249"],["<>:corenlp/c:S$<b>64<i>147<i>224<i>27<b>3","_17$<i>147<i>154","corenlp/p:KOUS","glemm/l:__nachdem","i:nachdem","mate/l:nachdem","mate/p:KOUS","opennlp/p:KOUS","s:nachdem","tt/l:nachdem$<b>129<b>255","tt/p:KOUS$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>155<i>171<i>21<b>4","_18$<i>155<i>158","corenlp/p:APPR","glemm/l:__vor","i:vor","mate/l:vor","mate/p:APPR","opennlp/p:APPR","s:vor","tt/l:vor$<b>129<b>246","tt/p:APPR$<b>129<b>246"],["_19$<i>159<i>166","corenlp/p:PIAT","glemm/l:__einig","glemm/l:__einig-","i:einiger","mate/l:einiger","mate/m:case:dat","mate/m:gender:fem","mate/m:number:sg","mate/p:PIAT","opennlp/p:PIAT","s:einiger","tt/l:einige$<b>129<b>254","tt/p:PIAT$<b>129<b>254"],["_20$<i>167<i>171","corenlp/p:NN","glemm/l:__Zeit","glemm/l:__zeit","i:zeit","mate/l:zeit","mate/m:case:dat","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Zeit","tt/l:Zeit$<b>129<b>254","tt/p:NN$<b>129<b>254"],["<>:corenlp/c:NP-OA$<b>64<i>172<i>216<i>26<b>4","_21$<i>172<i>179","corenlp/p:PIAT","glemm/l:__mehrer-","i:mehrere","mate/l:mehrere","mate/m:case:acc","mate/m:gender:masc","mate/m:number:pl","mate/p:PIAT","opennlp/p:PIAT","s:mehrere","tt/l:mehrere$<b>129<b>254","tt/p:PIAT$<b>129<b>254"],["_22$<i>180<i>190","corenlp/p:ADJA","glemm/l:__prominent","i:prominente","mate/l:prominent","mate/m:case:acc","mate/m:degree:pos","mate/m:gender:masc","mate/m:number:pl","mate/p:ADJA","opennlp/p:ADJA","s:prominente","tt/l:prominent$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_23$<i>191<i>201","corenlp/p:NN","glemm/l:_+Glied","glemm/l:_+mit-","glemm/l:__Mitglied","i:mitglieder","mate/l:mitglied","mate/m:case:acc","mate/m:gender:neut","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Mitglieder","tt/l:Mitglied$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>202<i>216<i>26<b>5","_24$<i>202<i>207","corenlp/p:PPOSAT","glemm/l:__ihr","glemm/l:__ihr-","i:ihren","mate/l:ihr","mate/m:case:acc","mate/m:gender:masc","mate/m:number:sg","mate/p:PPOSAT","opennlp/p:PPOSAT","s:ihren","tt/l:ihr$<b>129<b>254","tt/p:PPOSAT$<b>129<b>254"],["_25$<i>208<i>216","corenlp/p:NN","glemm/l:_+Tritt","glemm/l:_+aus-","glemm/l:__Austritt","i:austritt","mate/l:austritt","mate/m:case:acc","mate/m:gender:masc","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Austritt","tt/l:Austritt$<b>129<b>255","tt/p:NN$<b>129<b>255"],["_26$<i>217<i>224","glemm/l:__erklären","i:erklärt","mate/l:erklären","mate/p:VVPP","opennlp/p:VVFIN","s:erklärt","tt/l:erklären$<b>129<b>189","tt/l:erklären$<b>129<b>65","tt/p:VVFIN$<b>129<b>65","tt/p:VVPP$<b>129<b>189"],["_27$<i>225<i>228","corenlp/p:KON","glemm/l:__und","i:und","mate/l:und","mate/p:KON","opennlp/p:KON","s:und","tt/l:und$<b>129<b>255","tt/p:KON$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>229<i>293<i>34<b>3","<>:corenlp/c:S$<b>64<i>229<i>352<i>43<b>2","_28$<i>229<i>234","corenlp/p:APPR","glemm/l:__unter","i:unter","mate/l:unter","mate/p:APPR","opennlp/p:APPR","s:unter","tt/l:unter$<b>129<b>254","tt/p:APPR$<b>129<b>254"],["_29$<i>235<i>238","corenlp/p:ART","glemm/l:__d-","i:dem","mate/l:der","mate/m:case:dat","mate/m:gender:masc","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:dem","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_30$<i>239<i>244","corenlp/p:NN","glemm/l:__Name","i:namen","mate/l:name","mate/m:case:dat","mate/m:gender:masc","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Namen","tt/l:Name$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>245<i>293<i>34<b>4","_31$<i>245<i>262","glemm/l:++-ung","glemm/l:++bewegen","glemm/l:+_Bewegung","glemm/l:+_Einheit","glemm/l:__Einheitsbewegung","i:\"einheitsbewegung","mate/l:\"einheitsbewegung","mate/m:case:nom","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:\"Einheitsbewegung"],["<>:corenlp/c:NP$<b>64<i>263<i>293<i>34<b>5","_32$<i>263<i>266","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_33$<i>267<i>282","corenlp/p:ADJA","glemm/l:_+-al","glemm/l:_+-isch","glemm/l:_+-ist","glemm/l:_+Sozi","glemm/l:_+Sozialist","glemm/l:_+sozial","glemm/l:__sozialistisch","i:sozialistischen","mate/l:sozialistisch","mate/m:case:gen","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:sozialistischen","tt/l:sozialistisch$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_34$<i>283<i>294","glemm/l:__Initiative","glemm/l:__initiativ","i:initiative\"","mate/l:initiative\"","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Initiative\""],["<>:corenlp/c:NP-SB$<b>64<i>295<i>327<i>39<b>4","<>:corenlp/c:S-SB$<b>64<i>295<i>352<i>43<b>3","_35$<i>295<i>299","corenlp/p:ART","glemm/l:__ein","glemm/l:__eine","glemm/l:__einen","i:eine","mate/l:ein","mate/m:case:acc","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:eine","tt/l:eine$<b>129<b>253","tt/p:ART$<b>129<b>253"],["_36$<i>300<i>304","corenlp/p:ADJA","glemm/l:__neu","i:neue","mate/l:neu","mate/m:case:acc","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:neue","tt/l:neu$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_37$<i>305<i>315","corenlp/p:ADJA","glemm/l:__Politi","glemm/l:__politisch","glemm/l:__sch","i:politische","mate/l:politisch","mate/m:case:acc","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:politische","tt/l:politisch$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_38$<i>316<i>327","corenlp/p:NN","glemm/l:_+-ung","glemm/l:_+gruppieren","glemm/l:__Gruppierung","i:gruppierung","mate/l:gruppierung","mate/m:case:acc","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Gruppierung","tt/l:Gruppierung$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>328<i>337<i>41<b>5","<>:corenlp/c:VP$<b>64<i>328<i>345<i>42<b>4","_39$<i>328<i>331","corenlp/p:APPRART","glemm/l:__in","i:ins","mate/l:in","mate/m:case:acc","mate/m:gender:neut","mate/m:number:sg","mate/p:APPRART","opennlp/p:APPRART","s:ins","tt/l:ins$<b>129<b>255","tt/p:APPRART$<b>129<b>255"],["_40$<i>332<i>337","corenlp/p:NN","glemm/l:__Leben","glemm/l:__leben","i:leben","mate/l:leben","mate/m:case:acc","mate/m:gender:neut","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Leben","tt/l:Leben$<b>129<b>255","tt/p:NN$<b>129<b>255"],["_41$<i>338<i>345","corenlp/p:VVPP","glemm/l:_+ge-","glemm/l:__rufen","i:gerufen","mate/l:rufen","mate/p:VVPP","opennlp/p:VVPP","s:gerufen","tt/l:rufen$<b>129<b>255","tt/p:VVPP$<b>129<b>255"],["_42$<i>346<i>352","corenlp/p:VAFIN","glemm/l:__haben","i:hatten","mate/l:haben","mate/m:mood:ind","mate/m:number:pl","mate/m:person:3","mate/m:tense:past","mate/p:VAFIN","opennlp/p:VAFIN","s:hatten","tt/l:haben$<b>129<b>255","tt/p:VAFIN$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>354<i>377<i>45<b>2","<>:corenlp/c:ROOT$<b>64<i>354<i>506<i>59<b>0","<>:corenlp/s:s$<b>64<i>354<i>506<i>59<b>0","<>:tt/s:s$<b>64<i>354<i>506<i>59<b>0","<>:opennlp/s:s$<b>64<i>354<i>506<i>59<b>0","<>:corenlp/c:S$<b>64<i>354<i>506<i>59<b>1","<>:base/s:s$<b>64<i>354<i>506<i>59<b>2","_43$<i>354<i>369","corenlp/p:NN","glemm/l:++-ung","glemm/l:++melden","glemm/l:+_Meldung","glemm/l:+_Presse","glemm/l:__Pressemeldung","i:pressemeldungen","mate/l:pressemeldung","mate/m:case:dat","mate/m:gender:fem","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Pressemeldungen","tt/l:Pressemeldung$<b>129<b>255","tt/p:NN$<b>129<b>255"],["_44$<i>370<i>377","corenlp/p:APPO","glemm/l:__zufolge","i:zufolge","mate/l:zufolge","mate/p:APPO","opennlp/p:APPO","s:zufolge","tt/l:zufolge$<b>129<b>254","tt/p:APPO$<b>129<b>254"],["_45$<i>378<i>383","corenlp/p:VAFIN","glemm/l:__haben","i:haben","mate/l:haben","mate/m:mood:ind","mate/m:number:pl","mate/m:person:3","mate/m:tense:pres","mate/p:VAFIN","opennlp/p:VAFIN","s:haben","tt/l:haben$<b>129<b>222","tt/l:haben$<b>129<b>32","tt/p:VAFIN$<b>129<b>222","tt/p:VAINF$<b>129<b>32"],["_46$<i>384<i>388","corenlp/p:PRF","glemm/l:__er/sie/es/sie","i:sich","mate/l:sich","mate/m:case:acc","mate/m:number:pl","mate/m:person:3","mate/p:PRF","opennlp/p:PRF","s:sich","tt/l:er|es|sie$<b>129<b>255","tt/p:PRF$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>389<i>436<i>53<b>2","_47$<i>389<i>391","corenlp/p:APPR","glemm/l:__in","i:in","mate/l:in","mate/p:APPR","opennlp/p:APPR","s:in","tt/l:in$<b>129<b>255","tt/p:APPR$<b>129<b>255"],["_48$<i>392<i>395","corenlp/p:ART","glemm/l:__d-","i:den","mate/l:der","mate/m:case:dat","mate/m:gender:neut","mate/m:number:pl","mate/p:ART","opennlp/p:ART","s:den","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_49$<i>396<i>403","corenlp/p:ADJA","glemm/l:__letzt-","i:letzten","mate/l:letzter","mate/m:case:dat","mate/m:degree:pos","mate/m:gender:neut","mate/m:number:pl","mate/p:ADJA","opennlp/p:ADJA","s:letzten","tt/l:letzt$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_50$<i>404<i>409","corenlp/p:NN","glemm/l:__Tag","glemm/l:__tagen","i:tagen","mate/l:tag","mate/m:case:dat","mate/m:gender:neut","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Tagen","tt/l:Tag$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>410<i>436<i>53<b>3","_51$<i>410<i>414","corenlp/p:CARD","glemm/l:__acht","i:acht","mate/l:acht","mate/p:CARD","opennlp/p:CARD","s:acht","tt/l:acht$<b>129<b>254","tt/p:CARD$<b>129<b>254"],["_52$<i>415<i>436","corenlp/p:NN","glemm/l:+_Organisation","glemm/l:+_Provinz","glemm/l:__Provinzorganisation","i:provinzorganisationen","mate/l:provinzorganisation","mate/m:case:acc","mate/m:gender:fem","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Provinzorganisationen","tt/p:NN$<b>129<b>254"],["<>:corenlp/c:NP-SB$<b>64<i>437<i>491<i>58<b>2","_53$<i>437<i>440","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_54$<i>441<i>461","corenlp/ne:I-MISC","corenlp/p:ADJA","glemm/l:++Demokrat","glemm/l:+_demokratisch","glemm/l:+_sozial","glemm/l:_+-isch","glemm/l:_+Sozialdemokrat","glemm/l:__sozialdemokratisch","i:sozialdemokratischen","mate/l:sozialdemokratisch","mate/m:case:gen","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:Sozialdemokratischen","tt/l:sozialdemokratisch$<b>129<b>245","tt/p:ADJA$<b>129<b>245"],["_55$<i>462<i>468","corenlp/p:NN","glemm/l:__Partei","i:partei","mate/l:partei","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Partei","tt/l:Partei$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>469<i>491<i>58<b>3","_56$<i>469<i>472","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>253","tt/p:ART$<b>129<b>253"],["_57$<i>473<i>491","glemm/l:++-ung","glemm/l:++bewegen","glemm/l:+_Bewegung","glemm/l:+_Einheit","glemm/l:__Einheitsbewegung","i:\"einheitsbewegung\"","mate/l:\"einheitsbewegung\"","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:\"Einheitsbewegung\""],["<>:corenlp/c:VP$<b>64<i>492<i>505<i>59<b>2","_58$<i>492<i>505","corenlp/p:VVPP","glemm/l:_+an-","glemm/l:_+geschlossen","glemm/l:_+schliessen","glemm/l:__angeschlossen","glemm/l:__anschliessen","i:angeschlossen","mate/l:anschließen","mate/p:VVPP","opennlp/p:VVPP","s:angeschlossen","tt/l:anschließen$<b>129<b>255","tt/p:VVPP$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>507<i>519<i>61<b>2","<>:corenlp/c:ROOT$<b>64<i>507<i>570<i>69<b>0","<>:corenlp/s:s$<b>64<i>507<i>570<i>69<b>0","<>:tt/s:s$<b>64<i>507<i>570<i>69<b>0","<>:opennlp/s:s$<b>64<i>507<i>570<i>69<b>0","<>:corenlp/c:S$<b>64<i>507<i>570<i>69<b>1","<>:base/s:s$<b>64<i>507<i>570<i>69<b>2","_59$<i>507<i>509","corenlp/p:APPR","glemm/l:__zu","i:zu","mate/l:zu","mate/p:APPR","opennlp/p:APPR","s:zu","tt/l:zu$<b>129<b>141","tt/l:zu$<b>129<b>108","tt/p:APPR$<b>129<b>141","tt/p:PTKA$<b>129<b>108"],["_60$<i>510<i>515","corenlp/p:PPER","glemm/l:__sie","i:ihnen","mate/l:ihnen","mate/m:case:dat","mate/m:gender:*","mate/m:number:pl","mate/m:person:3","mate/p:PPER","opennlp/p:PPER","s:ihnen","tt/l:sie$<b>129<b>255","tt/p:PPER$<b>129<b>255"],["_61$<i>516<i>523","glemm/l:_+ge-","glemm/l:_+hören","glemm/l:__gehören","i:gehören","mate/l:gehören","mate/m:mood:ind","mate/m:number:pl","mate/m:person:3","mate/m:tense:pres","mate/p:VVFIN","opennlp/p:VVFIN","s:gehören","tt/l:gehören$<b>129<b>252","tt/p:VVFIN$<b>129<b>252"],["<>:corenlp/c:NP-SB$<b>64<i>524<i>540<i>64<b>2","_62$<i>524<i>527","corenlp/p:ART","glemm/l:__d-","i:die","mate/l:der","mate/m:case:acc","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:die","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_63$<i>528<i>540","corenlp/p:NN","glemm/l:__Organisation","i:organisation","mate/l:organisation","mate/m:case:acc","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Organisation","tt/l:Organisation$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>541<i>569<i>69<b>2","_64$<i>541<i>544","corenlp/p:APPR","glemm/l:__von","i:von","mate/l:von","mate/p:APPR","opennlp/p:APPR","s:von","tt/l:von$<b>129<b>254","tt/p:APPR$<b>129<b>254"],["<>:corenlp/c:CNP$<b>64<i>545<i>569<i>69<b>3","_65$<i>545<i>551","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Trient","i:trient","mate/l:trient","mate/m:case:dat","mate/m:gender:neut","mate/m:number:sg","mate/p:NE","opennlp/p:NN","s:Trient","tt/l:Trient$<b>129<b>255","tt/p:NE$<b>129<b>255"],["_66$<i>553<i>558","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Bozen","i:bozen","mate/l:bozen","mate/m:case:dat","mate/m:gender:neut","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Bozen","tt/l:Bozen$<b>129<b>255","tt/p:NE$<b>129<b>255"],["_67$<i>559<i>562","corenlp/p:KON","glemm/l:__und","i:und","mate/l:und","mate/p:KON","opennlp/p:KON","s:und","tt/l:und$<b>129<b>255","tt/p:KON$<b>129<b>255"],["_68$<i>563<i>569","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Triest","i:triest","mate/l:triest","mate/m:case:dat","mate/m:gender:neut","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Triest","tt/l:Triest$<b>129<b>255","tt/p:NE$<b>129<b>255"],["<>:corenlp/c:NP-SB$<b>64<i>571<i>625<i>75<b>2","<>:corenlp/c:ROOT$<b>64<i>571<i>703<i>84<b>0","<>:corenlp/s:s$<b>64<i>571<i>703<i>84<b>0","<>:tt/s:s$<b>64<i>571<i>703<i>84<b>0","<>:opennlp/s:s$<b>64<i>571<i>703<i>84<b>0","<>:corenlp/c:S$<b>64<i>571<i>703<i>84<b>1","<>:base/s:s$<b>64<i>571<i>703<i>84<b>2","_69$<i>571<i>574","corenlp/p:ART","glemm/l:__d-","i:die","mate/l:der","mate/m:case:acc","mate/m:gender:fem","mate/m:number:pl","mate/p:ART","opennlp/p:ART","s:die","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_70$<i>575<i>596","corenlp/p:NN","glemm/l:+_Organisation","glemm/l:+_Provinz","glemm/l:__Provinzorganisation","i:provinzorganisationen","mate/l:provinzorganisation","mate/m:case:acc","mate/m:gender:fem","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Provinzorganisationen","tt/p:NN$<b>129<b>254"],["<>:corenlp/c:CNP$<b>64<i>597<i>625<i>75<b>3","_71$<i>597<i>604","corenlp/ne:I-ORG","corenlp/p:NE","glemm/l:__Treviso","i:treviso","mate/l:treviso","mate/m:case:nom","mate/m:gender:masc","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Treviso","tt/l:Treviso$<b>129<b>255","tt/p:NE$<b>129<b>255"],["_72$<i>606<i>613","corenlp/ne:I-LOC","corenlp/p:NE","glemm/l:__Bergamo","i:bergamo","mate/l:bergamo","mate/m:case:nom","mate/m:gender:masc","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Bergamo","tt/l:Bergamo$<b>129<b>255","tt/p:NE$<b>129<b>255"],["_73$<i>614<i>617","corenlp/p:KON","glemm/l:__und","i:und","mate/l:und","mate/p:KON","opennlp/p:KON","s:und","tt/l:und$<b>129<b>255","tt/p:KON$<b>129<b>255"],["_74$<i>618<i>625","corenlp/ne:I-LOC","corenlp/p:NE","i:sondrio","mate/l:sondrio","mate/m:case:nom","mate/m:gender:masc","mate/m:number:sg","mate/p:NE","opennlp/p:NE","s:Sondrio","tt/p:NE$<b>129<b>212","tt/p:NN$<b>129<b>42"],["_75$<i>626<i>637","corenlp/p:VVFIN","glemm/l:_+be-","glemm/l:_+schliessen","glemm/l:__beschliessen","i:beschlossen","mate/l:beschließen","mate/p:VVPP","opennlp/p:VVPP","s:beschlossen","tt/l:beschließen$<b>129<b>174","tt/l:beschließen$<b>129<b>80","tt/p:VVFIN$<b>129<b>174","tt/p:VVPP$<b>129<b>80"],["<>:corenlp/c:PP$<b>64<i>638<i>666<i>79<b>2","_76$<i>638<i>641","corenlp/p:APPR","glemm/l:__mit","i:mit","mate/l:mit","mate/p:APPR","opennlp/p:APPR","s:mit","tt/l:mit$<b>129<b>253","tt/p:APPR$<b>129<b>253"],["<>:corenlp/c:AP$<b>64<i>643<i>657<i>78<b>3","_77$<i>642<i>657","glemm/l:_+überwältigen","glemm/l:__überwältigend","i:überwältigender","mate/l:überwältigend","mate/m:case:dat","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:überwältigender","tt/l:überwältigend$<b>129<b>254","tt/p:ADJA$<b>129<b>254"],["_78$<i>658<i>666","corenlp/p:NN","glemm/l:_+-heit","glemm/l:_+Mehr","glemm/l:__Mehrheit","i:mehrheit","mate/l:mehrheit","mate/m:case:dat","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Mehrheit","tt/l:Mehrheit$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP-OA$<b>64<i>667<i>702<i>84<b>2","_79$<i>667<i>670","corenlp/p:ART","glemm/l:__d-","i:den","mate/l:der","mate/m:case:acc","mate/m:gender:masc","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:den","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_80$<i>671<i>679","corenlp/p:NN","glemm/l:_+Tritt","glemm/l:_+aus-","glemm/l:__Austritt","i:austritt","mate/l:austritt","mate/m:case:acc","mate/m:gender:masc","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Austritt","tt/l:Austritt$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:PP$<b>64<i>680<i>702<i>84<b>3","_81$<i>680<i>683","corenlp/p:APPR","glemm/l:__aus","i:aus","mate/l:aus","mate/p:APPR","opennlp/p:APPR","s:aus","tt/l:aus$<b>129<b>247","tt/p:APPR$<b>129<b>247"],["_82$<i>684<i>687","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:dat","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_83$<i>688<i>702","corenlp/p:NN","glemm/l:__Partei","glemm/l:__Saragat","i:saragat-partei","mate/l:saragat-partei","mate/m:case:dat","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Saragat-Partei","tt/p:NN$<b>129<b>252"],["<>:corenlp/c:PP$<b>64<i>704<i>767<i>91<b>2","<>:corenlp/c:ROOT$<b>64<i>704<i>836<i>98<b>0","<>:corenlp/s:s$<b>64<i>704<i>836<i>98<b>0","<>:tt/s:s$<b>64<i>704<i>836<i>98<b>0","<>:opennlp/s:s$<b>64<i>704<i>836<i>98<b>0","<>:corenlp/c:S$<b>64<i>704<i>836<i>98<b>1","<>:base/s:s$<b>64<i>704<i>836<i>98<b>2","_84$<i>704<i>707","corenlp/p:APPR","glemm/l:__von","i:von","mate/l:von","mate/p:APPR","opennlp/p:APPR","s:von","tt/l:von$<b>129<b>254","tt/p:APPR$<b>129<b>254"],["_85$<i>708<i>711","corenlp/p:ART","glemm/l:__d-","i:den","mate/l:der","mate/m:case:dat","mate/m:gender:masc","mate/m:number:pl","mate/p:ART","opennlp/p:ART","s:den","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_86$<i>712<i>714","corenlp/p:CARD","i:98","mate/l:98","mate/p:CARD","opennlp/p:CARD","s:98","tt/l:98$<b>129<b>255","tt/p:CARD$<b>129<b>255"],["_87$<i>715<i>735","corenlp/p:NN","glemm/l:+_Jugend","glemm/l:+_Organisation","glemm/l:__Jugendorganisation","i:jugendorganisationen","mate/l:jugendorganisation","mate/m:case:dat","mate/m:gender:fem","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:Jugendorganisationen","tt/l:Jugendorganisation$<b>129<b>255","tt/p:NN$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>736<i>767<i>91<b>3","_88$<i>736<i>739","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_89$<i>740<i>760","corenlp/ne:I-MISC","corenlp/p:ADJA","glemm/l:++Demokrat","glemm/l:+_demokratisch","glemm/l:+_sozial","glemm/l:_+-isch","glemm/l:_+Sozialdemokrat","glemm/l:__sozialdemokratisch","i:sozialdemokratischen","mate/l:sozialdemokratisch","mate/m:case:gen","mate/m:degree:pos","mate/m:gender:fem","mate/m:number:sg","mate/p:ADJA","opennlp/p:ADJA","s:Sozialdemokratischen","tt/l:sozialdemokratisch$<b>129<b>245","tt/p:ADJA$<b>129<b>245"],["_90$<i>761<i>767","corenlp/p:NN","glemm/l:__Partei","i:partei","mate/l:partei","mate/m:case:gen","mate/m:gender:fem","mate/m:number:sg","mate/p:NN","opennlp/p:NN","s:Partei","tt/l:Partei$<b>129<b>255","tt/p:NN$<b>129<b>255"],["_91$<i>768<i>773","corenlp/p:VAFIN","glemm/l:__haben","i:haben","mate/l:haben","mate/m:mood:ind","mate/m:number:pl","mate/m:person:3","mate/m:tense:pres","mate/p:VAFIN","opennlp/p:VAFIN","s:haben","tt/l:haben$<b>129<b>233","tt/p:VAFIN$<b>129<b>233"],["_92$<i>774<i>778","corenlp/p:PRF","glemm/l:__er/sie/es/sie","i:sich","mate/l:sich","mate/m:case:acc","mate/m:number:pl","mate/m:person:3","mate/p:PRF","opennlp/p:PRF","s:sich","tt/l:er|es|sie$<b>129<b>255","tt/p:PRF$<b>129<b>255"],["<>:corenlp/c:NP-SB$<b>64<i>779<i>821<i>98<b>2","_93$<i>779<i>789","corenlp/p:ADV","glemm/l:__inzwischen","i:inzwischen","mate/l:inzwischen","mate/p:ADV","opennlp/p:ADV","s:inzwischen","tt/l:inzwischen$<b>129<b>255","tt/p:ADV$<b>129<b>255"],["_94$<i>790<i>792","corenlp/p:CARD","i:90","mate/l:90","mate/p:CARD","opennlp/p:CARD","s:90","tt/l:90$<b>129<b>255","tt/p:CARD$<b>129<b>255"],["<>:corenlp/c:NP$<b>64<i>793<i>821<i>98<b>3","_95$<i>793<i>796","corenlp/p:ART","glemm/l:__d-","i:der","mate/l:der","mate/m:case:gen","mate/m:gender:masc","mate/m:number:pl","mate/p:ART","opennlp/p:ART","s:der","tt/l:die$<b>129<b>254","tt/p:ART$<b>129<b>254"],["_96$<i>797<i>802","corenlp/p:ADJA","glemm/l:__neu","i:neuen","mate/l:neu","mate/m:case:gen","mate/m:degree:pos","mate/m:gender:masc","mate/m:number:pl","mate/p:ADJA","opennlp/p:ADJA","s:neuen","tt/l:neu$<b>129<b>255","tt/p:ADJA$<b>129<b>255"],["_97$<i>803<i>821","glemm/l:++-ung","glemm/l:++bewegen","glemm/l:+_Bewegung","glemm/l:+_Einheit","glemm/l:__Einheitsbewegung","i:\"einheitsbewegung\"","mate/l:\"einheitsbewegung\"","mate/m:case:gen","mate/m:gender:masc","mate/m:number:pl","mate/p:NN","opennlp/p:NN","s:\"Einheitsbewegung\""],["<>:corenlp/c:VP$<b>64<i>822<i>835<i>99<b>2","_98$<i>822<i>835","corenlp/p:VVPP","glemm/l:_+an-","glemm/l:_+geschlossen","glemm/l:_+schliessen","glemm/l:__angeschlossen","glemm/l:__anschliessen","i:angeschlossen","mate/l:anschließen","mate/p:VVPP","opennlp/p:VVPP","s:angeschlossen","tt/l:anschließen$<b>129<b>255","tt/p:VVPP$<b>129<b>255"]],"name":"tokens"},"corpusSigle":"BZK","license":"ACA-NC-LC","textDomain":"Politik","docTitle":"Neues Deutschland, Jahrgangsquerschnitt 1959","textSigle":"BZK_D59.00089","creationDate":"19590219","title":"Saragat-Partei zerfällt","pubDate":"19590219","textTypeRef":"Tageszeitung"}
\ No newline at end of file
diff --git a/lib/KorAP/Field/MultiTermToken.pm b/lib/KorAP/Field/MultiTermToken.pm
index e658f0d..4884e7f 100644
--- a/lib/KorAP/Field/MultiTermToken.pm
+++ b/lib/KorAP/Field/MultiTermToken.pm
@@ -109,6 +109,11 @@
# Both are attributes
# Order attributes by reference id
if (index($a->[5], '@:') == 0 && index($b->[5], '@:') == 0) {
+
+
+# use Data::Dumper;
+# die Dumper $a;
+
my ($a_id) = ($a->[0] =~ m/^<s>(\d+)/);
my ($b_id) = ($b->[0] =~ m/^<s>(\d+)/);
if ($a_id > $b_id) {
diff --git a/lib/KorAP/Index/Mate/Morpho2.pm b/lib/KorAP/Index/Mate/MorphoAttr.pm
similarity index 68%
rename from lib/KorAP/Index/Mate/Morpho2.pm
rename to lib/KorAP/Index/Mate/MorphoAttr.pm
index e032f2f..74ba26b 100644
--- a/lib/KorAP/Index/Mate/Morpho2.pm
+++ b/lib/KorAP/Index/Mate/MorphoAttr.pm
@@ -1,4 +1,4 @@
-package KorAP::Index::Mate::Morpho;
+package KorAP::Index::Mate::MorphoAttr;
use KorAP::Index::Base;
# This attaches morphological information as attributes to the pos
@@ -15,11 +15,12 @@
my $content = $token->hash->{fs}->{f};
- my ($found, $pos, $msd, $id);
+ my ($found, $pos, $msd, $tui);
my $capital = 0;
foreach my $f (@{$content->{fs}->{f}}) {
+
#pos
if (($f->{-name} eq 'pos') && ($found = $f->{'#text'})) {
$pos = $found;
@@ -37,18 +38,32 @@
($found = $f->{'#text'}) &&
($found ne '_')) {
$msd = $found;
- $id = $mtt->id_counter;
+ $tui = $mtt->id_counter;
};
};
- $mtt->add(term => 'mate/m:' . $pos . ($id ? ('$<s>' . $id) : ''));
+ my %term = (
+ term => 'mate/p:' . $pos
+ );
+
+ # There are attributes needed
+ if ($tui) {
+ $term{pti} = 128;
+ $term{payload} = '<s>' . $tui
+ };;
+
+ $mtt->add(%term);
# MSD
if ($msd) {
foreach (split '\|', $msd) {
my ($x, $y) = split "=", $_;
# case, tense, number, mood, person, degree, gender
- $mtt->add(term => '@:' . $x . ($y ? '=' . $y : '') . '$<s>' . $id);
+ $mtt->add(
+ term => '@:' . $x . ($y ? '=' . $y : ''),
+ pti => 16,
+ payload => '<s>' . $tui
+ );
};
};
}) or return;
@@ -57,7 +72,7 @@
};
sub layer_info {
- ['mate/l=tokens', 'mate/m=tokens']
+ ['mate/l=tokens', 'mate/p=tokens']
};
1;
diff --git a/lib/KorAP/Index/TreeTagger/Morpho.pm b/lib/KorAP/Index/TreeTagger/Morpho.pm
index 989728b..487b78a 100644
--- a/lib/KorAP/Index/TreeTagger/Morpho.pm
+++ b/lib/KorAP/Index/TreeTagger/Morpho.pm
@@ -42,7 +42,10 @@
my %term = (
term => 'tt/l:' . $found
);
- $term{payload} = '<b>' . $certainty if $certainty;
+ if ($certainty) {
+ $term{pti} = 129;
+ $term{payload} = '<b>' . $certainty;
+ };
$mtt->add(%term);
};
@@ -51,7 +54,10 @@
my %term = (
term => 'tt/p:' . $found
);
- $term{payload} = '<b>' . $certainty if $certainty;
+ if ($certainty) {
+ $term{pti} = 129;
+ $term{payload} = '<b>' . $certainty;
+ };
$mtt->add(%term);
};
};
diff --git a/lib/KorAP/Index/TreeTagger/Sentences.pm b/lib/KorAP/Index/TreeTagger/Sentences.pm
index 37b49e0..1d62d9f 100644
--- a/lib/KorAP/Index/TreeTagger/Sentences.pm
+++ b/lib/KorAP/Index/TreeTagger/Sentences.pm
@@ -16,7 +16,8 @@
o_start => $span->o_start,
o_end => $span->o_end,
p_end => $span->p_end,
- payload => '<b>2' # Depth is 2 by default t/p/s
+ pti => 64,
+ payload => '<b>0' # Could be 2 as well t/p/s
);
$i++;
}
diff --git a/t/index/corpus/doc/text/mate/dependency.xml b/t/index/corpus/doc/text/mate/dependency.xml
new file mode 100644
index 0000000..eeb1186
--- /dev/null
+++ b/t/index/corpus/doc/text/mate/dependency.xml
@@ -0,0 +1,139 @@
+<?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="Corpus_Doc.0001"
+ version="KorA-0.2"
+ xmlns="http://ids-mannheim.de/ns/KorA">
+ <spanList>
+ <span from="0"
+ to="3">
+ <rel label="MO">
+ <span from="31"
+ to="35" />
+ </rel>
+ </span>
+ <span from="4"
+ to="11">
+ <rel label="NK">
+ <span from="24"
+ to="30" />
+ </rel>
+ </span>
+ <span from="12"
+ to="23">
+ <rel label="NK">
+ <span from="24"
+ to="30" />
+ </rel>
+ </span>
+ <span from="24"
+ to="30">
+ <rel label="NK">
+ <span from="0"
+ to="3" />
+ </rel>
+ </span>
+ <span from="31"
+ to="35">
+ <rel label="--"
+ type="unary" />
+ </span>
+ <span from="36"
+ to="39">
+ <rel label="NK">
+ <span from="40"
+ to="47" />
+ </rel>
+ </span>
+ <span from="40"
+ to="47">
+ <rel label="SB">
+ <span from="31"
+ to="35" />
+ </rel>
+ </span>
+ <span from="48"
+ to="51">
+ <rel label="NK">
+ <span from="52"
+ to="63" />
+ </rel>
+ </span>
+ <span from="52"
+ to="63">
+ <rel label="AG">
+ <span from="40"
+ to="47" />
+ </rel>
+ </span>
+ <span from="64"
+ to="73">
+ <rel label="NK">
+ <span from="52"
+ to="63" />
+ </rel>
+ </span>
+ <span from="74"
+ to="77">
+ <rel label="SVP">
+ <span from="31"
+ to="35" />
+ </rel>
+ </span>
+ <span from="77"
+ to="78">
+ <rel label="--">
+ <span from="74"
+ to="77" />
+ </rel>
+ </span>
+ <span from="79"
+ to="84">
+ <rel label="CP">
+ <span from="124"
+ to="128" />
+ </rel>
+ </span>
+ <span from="85"
+ to="88">
+ <rel label="NK">
+ <span from="89"
+ to="96" />
+ </rel>
+ </span>
+ <span from="89"
+ to="96">
+ <rel label="SB">
+ <span from="124"
+ to="128" />
+ </rel>
+ </span>
+ <span from="97"
+ to="101">
+ <rel label="OA">
+ <span from="112"
+ to="123" />
+ </rel>
+ </span>
+ <span from="102"
+ to="111">
+ <rel label="NK">
+ <span from="97"
+ to="101" />
+ </rel>
+ </span>
+ <span from="112"
+ to="123">
+ <rel label="OC">
+ <span from="124"
+ to="128" />
+ </rel>
+ </span>
+ <span from="124"
+ to="128">
+ <rel label="MO">
+ <span from="31"
+ to="35" />
+ </rel>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/mate/morpho.xml b/t/index/corpus/doc/text/mate/morpho.xml
new file mode 100644
index 0000000..bf1a1a9
--- /dev/null
+++ b/t/index/corpus/doc/text/mate/morpho.xml
@@ -0,0 +1,214 @@
+<?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="Corpus_Doc.0001" version="KorAP-0.4" xmlns="http://ids-mannheim.de/ns/KorAP">
+ <spanList>
+ <span from="0" id="s2_1" to="3">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">zu</f>
+ <f name="pos">APPRART</f>
+ <f name="msd">case=dat|number=sg|gender=neut</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="4" id="s2_2" to="11">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">letzter</f>
+ <f name="pos">ADJA</f>
+ <f name="msd">case=dat|number=sg|gender=neut|degree=pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="12" id="s2_3" to="23">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">kulturell</f>
+ <f name="pos">ADJA</f>
+ <f name="msd">case=gen|number=sg|gender=neut|degree=pos</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="24" id="s2_4" to="30">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">anlass</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=gen|number=sg|gender=neut</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="31" id="s2_5" to="35">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">laden</f>
+ <f name="pos">VVFIN</f>
+ <f name="msd">number=sg|person=3|tense=pres|mood=ind</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="36" id="s2_6" to="39">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">der</f>
+ <f name="pos">ART</f>
+ <f name="msd">case=acc|number=sg|gender=fem</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="40" id="s2_7" to="47">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">leitung</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=acc|number=sg|gender=fem</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="48" id="s2_8" to="51">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">der</f>
+ <f name="pos">ART</f>
+ <f name="msd">case=gen|number=sg|gender=neut</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="52" id="s2_9" to="63">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">schulheime</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=gen|number=sg|gender=neut</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="64" id="s2_10" to="73">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">hofbergli</f>
+ <f name="pos">NE</f>
+ <f name="msd">case=nom|number=sg|gender=*</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="74" id="s2_11" to="77">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">ein</f>
+ <f name="pos">PTKVZ</f>
+ <f name="msd">_</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="77" id="s2_12" to="78">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">--</f>
+ <f name="pos">$,</f>
+ <f name="msd">_</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="79" id="s2_13" to="84">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">bevor</f>
+ <f name="pos">KOUS</f>
+ <f name="msd">_</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="85" id="s2_14" to="88">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">der</f>
+ <f name="pos">ART</f>
+ <f name="msd">case=nom|number=sg|gender=masc</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="89" id="s2_15" to="96">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">betrieb</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=nom|number=sg|gender=masc</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="97" id="s2_16" to="101">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">ende</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=*|number=sg|gender=neut</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="102" id="s2_17" to="111">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">schuljahr</f>
+ <f name="pos">NN</f>
+ <f name="msd">case=*|number=sg|gender=masc</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="112" id="s2_18" to="123">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">einstellen</f>
+ <f name="pos">VVPP</f>
+ <f name="msd">_</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="124" id="s2_19" to="128">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">werden</f>
+ <f name="pos">VAFIN</f>
+ <f name="msd">number=sg|person=3|tense=pres|mood=ind</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/struct/structure.xml b/t/index/corpus/doc/text/struct/structure.xml
new file mode 100644
index 0000000..2ef6178
--- /dev/null
+++ b/t/index/corpus/doc/text/struct/structure.xml
@@ -0,0 +1,309 @@
+<?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="A01_APR.13047" xmlns="http://ids-mannheim.de/ns/KorAP" version="KorAP-0.4">
+ <spanList>
+ <span id="s0" from="0" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">idsText</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="version">1.0</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s1" from="0" to="0">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">idsHeader</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="version">1.1</f>
+ <f name="status">new</f>
+ <f name="TEIform">teiHeader</f>
+ <f name="pattern">text</f>
+ <f name="type">text</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s2" from="0" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">text</f>
+ </fs>
+ </span>
+ <span id="s3" from="0" to="0">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">front</f>
+ </fs>
+ </span>
+ <span id="s4" from="0" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">body</f>
+ </fs>
+ </span>
+ <span id="s5" from="0" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">div</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="n">0</f>
+ <f name="type">Zeitung</f>
+ <f name="complete">y</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s6" from="0" to="31">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">head</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="type">main</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s7" from="0" to="31">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s8" from="32" to="42">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">byline</f>
+ </fs>
+ </span>
+ <span id="s9" from="32" to="42">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s10" from="43" to="633">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">div</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="n">1</f>
+ <f name="type">section</f>
+ <f name="complete">y</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s11" from="43" to="633">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">p</f>
+ </fs>
+ </span>
+ <span id="s12" from="43" to="172">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s13" from="173" to="364">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s14" from="365" to="477">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s15" from="478" to="633">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s16" from="634" to="1008">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">div</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="n">1</f>
+ <f name="type">section</f>
+ <f name="complete">y</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s17" from="634" to="658">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">head</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="type">cross</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s18" from="634" to="658">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s19" from="659" to="664">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">byline</f>
+ </fs>
+ </span>
+ <span id="s20" from="659" to="664">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s21" from="665" to="1008">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">p</f>
+ </fs>
+ </span>
+ <span id="s22" from="665" to="789">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s23" from="790" to="865">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s24" from="866" to="1008">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s25" from="1009" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">div</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="n">1</f>
+ <f name="type">section</f>
+ <f name="complete">y</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s26" from="1009" to="1036">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">head</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="type">cross</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s27" from="1009" to="1036">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s28" from="1037" to="1050">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">byline</f>
+ </fs>
+ </span>
+ <span id="s29" from="1037" to="1050">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s30" from="1051" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">p</f>
+ </fs>
+ </span>
+ <span id="s31" from="1051" to="1220">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s32" from="1221" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">s</f>
+ <f name="attr">
+ <fs type="attr">
+ <f name="broken">no</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span id="s33" from="1327" to="1327">
+ <fs type="struct" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="name">back</f>
+ </fs>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/tree_tagger/morpho.xml b/t/index/corpus/doc/text/tree_tagger/morpho.xml
new file mode 100644
index 0000000..e229cec
--- /dev/null
+++ b/t/index/corpus/doc/text/tree_tagger/morpho.xml
@@ -0,0 +1,216 @@
+<?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="Corpus_Doc.0001" version="KorAP-0.4" xmlns="http://ids-mannheim.de/ns/KorAP">
+ <spanList>
+ <span from="0" id="s_7" to="3">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">zum</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">APPRART</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="4" id="s_8" to="11">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">letzt</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">ADJA</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="12" id="s_9" to="23">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">kulturell</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">ADJA</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="24" id="s_10" to="30">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Anlaß</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="31" id="s_11" to="35">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">laden</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">VVFIN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="36" id="s_12" to="39">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">die</f>
+ <f name="certainty">0.997413</f>
+ <f name="ctag">ART</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="40" id="s_13" to="47">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Leitung</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="48" id="s_14" to="51">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">die</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">ART</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="52" id="s_15" to="63">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Schulheim</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="64" id="s_16" to="73">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">UNKNOWN</f>
+ <f name="certainty">0.912122</f>
+ <f name="ctag">NE</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="74" id="s_17" to="77">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">ein</f>
+ <f name="certainty">0.992479</f>
+ <f name="ctag">PTKVZ</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="77" id="s_18" to="78">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">,</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">$,</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="79" id="s_19" to="84">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">bevor</f>
+ <f name="certainty">0.999168</f>
+ <f name="ctag">KOUS</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="85" id="s_20" to="88">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">die</f>
+ <f name="certainty">0.999135</f>
+ <f name="ctag">ART</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="89" id="s_21" to="96">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Betrieb</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="97" id="s_22" to="101">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Ende</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="102" id="s_23" to="111">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">Schuljahr</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">NN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="112" id="s_24" to="123">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">einstellen</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">VVPP</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ <span from="124" id="s_25" to="128">
+ <fs type="lex" xmlns="http://www.tei-c.org/ns/1.0">
+ <f name="lex">
+ <fs>
+ <f name="lemma">werden</f>
+ <f name="certainty">1.000000</f>
+ <f name="ctag">VAFIN</f>
+ </fs>
+ </f>
+ </fs>
+ </span>
+ </spanList>
+</layer>
diff --git a/t/index/corpus/doc/text/tree_tagger/sentences.xml b/t/index/corpus/doc/text/tree_tagger/sentences.xml
new file mode 100644
index 0000000..cd2b00b
--- /dev/null
+++ b/t/index/corpus/doc/text/tree_tagger/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 xmlns="http://ids-mannheim.de/ns/KorAP" version="KorAP-0.4" docid="Corpus_Doc.0001">
+ <spanList>
+ <span from="0" to="130" />
+ </spanList>
+</layer>
diff --git a/t/index/glemm_morpho.t b/t/index/glemm_morpho.t
index 49157d5..650cecc 100644
--- a/t/index/glemm_morpho.t
+++ b/t/index/glemm_morpho.t
@@ -44,6 +44,7 @@
is($data->{stream}->[0]->[2], 'glemm/l:__zu', 'Lemma');
is($data->{stream}->[1]->[1], 'glemm/l:__letzt-', 'Lemma');
+
is($data->{stream}->[3]->[1], 'glemm/l:_+an-', 'Lemma');
is($data->{stream}->[3]->[2], 'glemm/l:_+lass', 'Lemma');
is($data->{stream}->[3]->[3], 'glemm/l:__Anlass', 'Lemma');
diff --git a/t/index/mate_dependency.t b/t/index/mate_dependency.t
new file mode 100644
index 0000000..b4e4150
--- /dev/null
+++ b/t/index/mate_dependency.t
@@ -0,0 +1,45 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use utf8;
+use Test::More skip_all => 'Not yet implemented';
+use Scalar::Util qw/weaken/;
+use Data::Dumper;
+
+use_ok('KorAP::Document');
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text');
+
+ok(my $doc = KorAP::Document->new(
+ path => $path . '/'
+), 'Load Korap::Document');
+
+like($doc->path, qr!$path/$!, 'Path');
+ok($doc->parse, 'Parse document');
+
+ok($doc->primary->data, 'Primary data in existence');
+is($doc->primary->data_length, 129, 'Data length');
+
+use_ok('KorAP::Tokenizer');
+
+ok(my $tokens = KorAP::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => 'OpenNLP',
+ layer => 'Tokens',
+ name => 'tokens'
+), 'New Tokenizer');
+
+ok($tokens->parse, 'Parse');
+
+ok($tokens->add('Mate', 'Dependency'), 'Add Structure');
+
+# my $data = $tokens->to_data->{data};
+
+done_testing;
+
+__END__
+
diff --git a/t/index/mate_morpho.t b/t/index/mate_morpho.t
new file mode 100644
index 0000000..16dde94
--- /dev/null
+++ b/t/index/mate_morpho.t
@@ -0,0 +1,62 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use utf8;
+use Test::More;
+use Scalar::Util qw/weaken/;
+use Data::Dumper;
+
+use_ok('KorAP::Document');
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text');
+
+ok(my $doc = KorAP::Document->new(
+ path => $path . '/'
+), 'Load Korap::Document');
+
+like($doc->path, qr!$path/$!, 'Path');
+ok($doc->parse, 'Parse document');
+
+ok($doc->primary->data, 'Primary data in existence');
+is($doc->primary->data_length, 129, 'Data length');
+
+use_ok('KorAP::Tokenizer');
+
+ok(my $tokens = KorAP::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => 'OpenNLP',
+ layer => 'Tokens',
+ name => 'tokens'
+), 'New Tokenizer');
+
+ok($tokens->parse, 'Parse');
+
+ok($tokens->add('Mate', 'Morpho'), 'Add Structure');
+
+my $data = $tokens->to_data->{data};
+
+like($data->{foundries}, qr!mate/morpho!, 'data');
+like($data->{layerInfos}, qr!mate/p=tokens!, 'data');
+like($data->{layerInfos}, qr!mate/l=tokens!, 'data');
+like($data->{layerInfos}, qr!mate/m=tokens!, 'data');
+
+is($data->{stream}->[0]->[3], 'mate/l:zu', 'POS');
+is($data->{stream}->[0]->[4], 'mate/m:case:dat', 'POS');
+is($data->{stream}->[0]->[5], 'mate/m:gender:neut', 'POS');
+is($data->{stream}->[0]->[6], 'mate/m:number:sg', 'POS');
+is($data->{stream}->[0]->[7], 'mate/p:APPRART', 'POS');
+
+is($data->{stream}->[-1]->[2], 'mate/l:werden', 'POS');
+is($data->{stream}->[-1]->[3], 'mate/m:mood:ind', 'POS');
+is($data->{stream}->[-1]->[4], 'mate/m:number:sg', 'POS');
+is($data->{stream}->[-1]->[5], 'mate/m:person:3', 'POS');
+is($data->{stream}->[-1]->[6], 'mate/m:tense:pres', 'POS');
+is($data->{stream}->[-1]->[7], 'mate/p:VAFIN', 'POS');
+
+done_testing;
+
+__END__
diff --git a/t/index/mate_morpho_attr.t b/t/index/mate_morpho_attr.t
new file mode 100644
index 0000000..2833c4e
--- /dev/null
+++ b/t/index/mate_morpho_attr.t
@@ -0,0 +1,61 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use utf8;
+use Test::More;
+use Scalar::Util qw/weaken/;
+use Data::Dumper;
+
+use_ok('KorAP::Document');
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text');
+
+ok(my $doc = KorAP::Document->new(
+ path => $path . '/'
+), 'Load Korap::Document');
+
+like($doc->path, qr!$path/$!, 'Path');
+ok($doc->parse, 'Parse document');
+
+ok($doc->primary->data, 'Primary data in existence');
+is($doc->primary->data_length, 129, 'Data length');
+
+use_ok('KorAP::Tokenizer');
+
+ok(my $tokens = KorAP::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => 'OpenNLP',
+ layer => 'Tokens',
+ name => 'tokens'
+), 'New Tokenizer');
+
+ok($tokens->parse, 'Parse');
+
+ok($tokens->add('Mate', 'MorphoAttr'), 'Add Structure');
+
+my $data = $tokens->to_data->{data};
+
+like($data->{foundries}, qr!mate/morphoattr!, 'data');
+like($data->{layerInfos}, qr!mate/p=tokens!, 'data');
+like($data->{layerInfos}, qr!mate/l=tokens!, 'data');
+
+is($data->{stream}->[0]->[1], '@:gender=neut$<b>16<s>1', 'POS');
+is($data->{stream}->[0]->[2], '@:number=sg$<b>16<s>1', 'POS');
+is($data->{stream}->[0]->[3], '@:case=dat$<b>16<s>1', 'POS');
+is($data->{stream}->[0]->[6], 'mate/l:zu', 'Lemmata');
+is($data->{stream}->[0]->[7], 'mate/p:APPRART$<b>128<s>1', 'POS');
+
+is($data->{stream}->[-1]->[0], '@:mood=ind$<b>16<s>1', 'POS');
+is($data->{stream}->[-1]->[1], '@:tense=pres$<b>16<s>1', 'POS');
+is($data->{stream}->[-1]->[2], '@:person=3$<b>16<s>1', 'POS');
+is($data->{stream}->[-1]->[3], '@:number=sg$<b>16<s>1', 'POS');
+is($data->{stream}->[-1]->[6], 'mate/l:werden', 'Lemmata');
+is($data->{stream}->[-1]->[7], 'mate/p:VAFIN$<b>128<s>1', 'POS');
+
+done_testing;
+
+__END__
diff --git a/t/index/tt_morpho.t b/t/index/tt_morpho.t
new file mode 100644
index 0000000..f2b31c9
--- /dev/null
+++ b/t/index/tt_morpho.t
@@ -0,0 +1,61 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use utf8;
+use Test::More;
+use Scalar::Util qw/weaken/;
+use Data::Dumper;
+
+use_ok('KorAP::Document');
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text');
+
+ok(my $doc = KorAP::Document->new(
+ path => $path . '/'
+), 'Load Korap::Document');
+
+like($doc->path, qr!$path/$!, 'Path');
+ok($doc->parse, 'Parse document');
+
+ok($doc->primary->data, 'Primary data in existence');
+is($doc->primary->data_length, 129, 'Data length');
+
+use_ok('KorAP::Tokenizer');
+
+ok(my $tokens = KorAP::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => 'OpenNLP',
+ layer => 'Tokens',
+ name => 'tokens'
+), 'New Tokenizer');
+
+ok($tokens->parse, 'Parse');
+
+ok($tokens->add('TreeTagger', 'Morpho'), 'Add Structure');
+
+my $data = $tokens->to_data->{data};
+
+like($data->{foundries}, qr!treetagger/morpho!, 'data');
+like($data->{layerInfos}, qr!tt/p=tokens!, 'data');
+like($data->{layerInfos}, qr!tt/l=tokens!, 'data');
+
+is($data->{stream}->[0]->[4], 'tt/l:zum$<b>129<b>255', 'POS');
+is($data->{stream}->[0]->[5], 'tt/p:APPRART$<b>129<b>255', 'POS');
+
+is($data->{stream}->[3]->[3], 'tt/l:Anlaß$<b>129<b>255', 'POS');
+is($data->{stream}->[3]->[4], 'tt/p:NN$<b>129<b>255', 'POS');
+
+is($data->{stream}->[10]->[3], 'tt/l:ein$<b>129<b>253', 'POS');
+is($data->{stream}->[10]->[4], 'tt/p:PTKVZ$<b>129<b>253', 'POS');
+
+is($data->{stream}->[-1]->[3], 'tt/l:werden$<b>129<b>255', 'POS');
+is($data->{stream}->[-1]->[4], 'tt/p:VAFIN$<b>129<b>255', 'POS');
+
+done_testing;
+
+__END__
+
diff --git a/t/index/tt_sentences.t b/t/index/tt_sentences.t
new file mode 100644
index 0000000..3776197
--- /dev/null
+++ b/t/index/tt_sentences.t
@@ -0,0 +1,53 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use utf8;
+use Test::More;
+use Scalar::Util qw/weaken/;
+use Data::Dumper;
+
+use_ok('KorAP::Document');
+
+use File::Basename 'dirname';
+use File::Spec::Functions 'catdir';
+
+my $path = catdir(dirname(__FILE__), 'corpus', 'doc', 'text');
+
+ok(my $doc = KorAP::Document->new(
+ path => $path . '/'
+), 'Load Korap::Document');
+
+like($doc->path, qr!$path/$!, 'Path');
+ok($doc->parse, 'Parse document');
+
+ok($doc->primary->data, 'Primary data in existence');
+is($doc->primary->data_length, 129, 'Data length');
+
+use_ok('KorAP::Tokenizer');
+
+ok(my $tokens = KorAP::Tokenizer->new(
+ path => $doc->path,
+ doc => $doc,
+ foundry => 'OpenNLP',
+ layer => 'Tokens',
+ name => 'tokens'
+), 'New Tokenizer');
+
+ok($tokens->parse, 'Parse');
+
+ok($tokens->add('TreeTagger', 'Sentences'), 'Add Structure');
+
+my $data = $tokens->to_data->{data};
+
+#diag Dumper $data;
+
+like($data->{foundries}, qr!treetagger/sentences!, 'data');
+is($data->{stream}->[0]->[0], '-:tokens$<i>18', 'Number of tokens');
+is($data->{stream}->[0]->[1], '-:tt/sentences$<i>1', 'Number of paragraphs');
+is($data->{stream}->[0]->[2], '<>:tt/s:s$<b>64<i>0<i>130<i>17<b>0', 'Text');
+is($data->{stream}->[0]->[3], '_0$<i>0<i>3', 'Position');
+is($data->{stream}->[-1]->[0], '_17$<i>124<i>128', 'Position');
+
+done_testing;
+
+__END__