diff --git a/dnet-ariadneplus-container/src/main/resources/eu/dnetlib/cnr-site.properties b/dnet-ariadneplus-container/src/main/resources/eu/dnetlib/cnr-site.properties index 9fe6781..4a15625 100644 --- a/dnet-ariadneplus-container/src/main/resources/eu/dnetlib/cnr-site.properties +++ b/dnet-ariadneplus-container/src/main/resources/eu/dnetlib/cnr-site.properties @@ -33,8 +33,8 @@ msro.wf.mail.smtp.user = smtp-user msro.wf.mail.smtp.password = smtp-pwd msro.wf.mail.cc = manager@email.eu service.index.solr.rank.enable = true -services.publisher.oai.host = localhost -services.publisher.oai.port = 27017 +#services.publisher.oai.host = localhost +#services.publisher.oai.port = 27017 services.objectstore.dao = gridFSObjectstoreDao # AUTH dnet.modular.ui.authorization.mongo.host = localhost diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/CLARIN_README.txt b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/CLARIN_README.txt deleted file mode 100644 index c821a9d..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/CLARIN_README.txt +++ /dev/null @@ -1,8 +0,0 @@ -Getting the latest mappings: -1. wget "https://github.com/acdh-oeaw/ariadneplus_mapping/archive/development.zip" -2. Extract the zip -The workflow is configured to read from /var/lib/ariadneplus-data/clarin/ariadneplus_mapping-development/batch/x3ml-mappings - -Getting the latest records -1. Rename possibly existing folder results -2. Run prepareClarin.sh (with noHup or screen) \ No newline at end of file diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/prepareClarin.sh b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/prepareClarin.sh deleted file mode 100755 index a761d31..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/clarin/prepareClarin.sh +++ /dev/null @@ -1,59 +0,0 @@ -#!/bin/bash -# Author: Wolfgang Sauer. -# See https://support.d4science.org/issues/8626#change-58157 - -# this has to be changed ++++++++++++++++++++++++ -WORK_DIR=/var/lib/ariadneplus-data/clarin - -# fix paths ++++++++++++++++++++++++++++++++++++++ -HARVESTER_URL=https://vlo.clarin.eu/resultsets -RESULTSETS='clarin.tar.bz2 others.tar.bz2' -CMDI_PATH=results/cmdi -# end fix paths +++++++++++++++++++++++++++++++++ - -if [ -e $WORK_DIR/results ]; then - echo "removing old results..." - rm -rf $WORK_DIR/results -fi - -cd $WORK_DIR - -#download harvested records, unpack, clean -for RESULTSET in $RESULTSETS; do - #download tar - wget $HARVESTER_URL/$RESULTSET - - echo "unpacking $RESULTSET..." - #unpack CMDI 1.2 files - tar xjf $RESULTSET $CMDI_PATH - - #delete tar - rm $RESULTSET -done - -echo "correcting hdl string and reorganizing files by profile id..." - -find $WORK_DIR/$CMDI_PATH -name '*.xml'| while read -r file; do - echo "treating file $file" -# add http to hdl string - sed -i 's/hdl:/http:\/\/hdl.handle.net\//g' $file - -# organizing files by profile id - profileID=$(grep -oP '.+p_[0-9]+' $file|grep -oE p_[0-9]+) - if [ -n "$profileID" ]; then - outDir=$WORK_DIR/$CMDI_PATH/$profileID - else - outDir=$WORK_DIR/$CMDI_PATH/noProfileID - fi - - if [ ! -e $outDir ]; then - mkdir $outDir - fi - - mv $file $outDir -done - -echo "removing empty directories..." -rmdir --ignore-fail-on-non-empty $WORK_DIR/$CMDI_PATH - -echo "finished!" \ No newline at end of file diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/nodes/clarin_tds.xml.st b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/nodes/clarin_tds.xml.st deleted file mode 100644 index 2f17d72..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/nodes/clarin_tds.xml.st +++ /dev/null @@ -1,22 +0,0 @@ - -
- - - - - -
- - - - - - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/CLARIN_aggregation_wf.xml.st b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/CLARIN_aggregation_wf.xml.st deleted file mode 100644 index 725240a..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/CLARIN_aggregation_wf.xml.st +++ /dev/null @@ -1,150 +0,0 @@ - - -
- - - - - -
- - $name$ - $desc$ - - aggregator - $priority$ - - - - - INCREMENTAL - - - false - REFRESH - - - $tdsCsv$ - 4d94a3f0-a5c8-441e-a506-8328af17a6f3_VHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZXMvVHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZVR5cGU= - - e508ddc7-ff5e-45dc-9116-96a2201d0bc9_Q2xlYW5lckRTUmVzb3VyY2VzL0NsZWFuZXJEU1Jlc291cmNlVHlwZQ== - - - - transformed - REFRESH - - CIDOC - OAI - transformed - oaistore_ariadneplus - - - - Collect metadata - - - - - - - - - - - - - - - - - - - Transform records - - - - - - - - - - - - - - - - - - - - - - - - - - Index record - - - - - - - - - - - - - - - - - - - Send to OAI-PMH Publisher - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 9 9 9 ? * * - 10080 - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/JRR_publish_wf.xml.st b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/JRR_publish_wf.xml.st deleted file mode 100644 index ff7ecd6..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/JRR_publish_wf.xml.st +++ /dev/null @@ -1,55 +0,0 @@ - - -
- - - - - -
- - $name$ - $desc$ - - publishing - $priority$ - - - - - http://beta-ariadneplus.d4science.org:8080/ariadneplus/publish - http://beta-ariadneplus.d4science.org:8080/ariadneplus/virtuoso - - - - Feed the JRR - - - - - - - - - - - - - - - - - - - - - - - - - 9 9 9 ? * * - 10080 - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/x3m_aggregation_wf.xml.st b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/x3m_aggregation_wf.xml.st index fcdaeed..b6d749b 100644 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/x3m_aggregation_wf.xml.st +++ b/dnet-ariadneplus/src/main/resources/eu/dnetlib/ariadneplus/workflows/repo-hi/x3m_aggregation_wf.xml.st @@ -33,11 +33,7 @@ transformed REFRESH - CIDOC - OAI - transformed - oaistore_ariadneplus - + Collect metadata @@ -100,26 +96,8 @@ - - - - - Send to OAI-PMH Publisher - - - - - - - - - - - - - - + @@ -130,10 +108,6 @@ - - - - diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/OAIPublisherConfigurationDSResourceType/oai-configuration.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/OAIPublisherConfigurationDSResourceType/oai-configuration.xml deleted file mode 100644 index d117c95..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/OAIPublisherConfigurationDSResourceType/oai-configuration.xml +++ /dev/null @@ -1,52 +0,0 @@ - -
- - - - - -
- - - oai - ariadneplus - oaistore_ariadneplus - - - - - - - - - - - http://www.cidoc-crm.org/cidoc-crm/ - http://www.cidoc-crm.org/cidoc-crm/ - - - *=* - - - - - - - - - - - - - - SECURITY_PARAMETERS - -
\ No newline at end of file diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/JRRPublish_repo_hi_x3m.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/JRRPublish_repo_hi_x3m.xml deleted file mode 100644 index ca05ee3..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/JRRPublish_repo_hi_x3m.xml +++ /dev/null @@ -1,59 +0,0 @@ - - -
- - - - - -
- - PUBLISH ON JRR - publish on catalogue and resource registry - - Publish - Content Provider - - REPO_HI - 20 - - - - - Verify if DS is pending - - - - - - - - - - Validate DS - - - - - - - Create Workflow - - - - - - - - - - - - - - 9 9 9 ? * * - 10080 - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/clarin_ds_tds_generation.wf.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/clarin_ds_tds_generation.wf.xml deleted file mode 100644 index 95dad16..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/clarin_ds_tds_generation.wf.xml +++ /dev/null @@ -1,46 +0,0 @@ - -
- - - - - -
- - Update DS and TDS for Clarin - Update DS and TDS for Clarin - - Consistency - 30 - - - /var/lib/parthenos-data/clarin/parthenos_mapping-development/batch/x3ml-mappings - file:///var/lib/dnet/data/parthenos/clarin/results/cmdi - //*[local-name()="MdSelfLink"] - 18b60922-44a4-4c0d-ab24-4b9835186a0a_UmVwb3NpdG9yeVNlcnZpY2VSZXNvdXJjZXMvUmVwb3NpdG9yeVNlcnZpY2VSZXNvdXJjZVR5cGU= - parthenos___::clarin - - - - Update DS and TDS for Clarin - - - - - - - - - - - - - - - - 29 5 22 ? * * - 10080 - - - -
\ No newline at end of file diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/feed_oai_template.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/feed_oai_template.xml deleted file mode 100644 index f879cdd..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/feed_oai_template.xml +++ /dev/null @@ -1,59 +0,0 @@ - -
- - - - - -
- - - - - - - - - - - - Fetch records from MDStore - - - - - - - - - - Clean original records - - - - - - - - - - - - - - Update set counters - - - - - - - - - - - - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/post_feed_oai_template.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/post_feed_oai_template.xml deleted file mode 100644 index a939752..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/post_feed_oai_template.xml +++ /dev/null @@ -1,73 +0,0 @@ - -
- - - - - -
- - - - - - - - - - - - - Create composite indexes for the OAI store - - - - - - - - - - - - - Ensure an index exists on fields as specified in the configuration profile - - - - - - - - - - - - Reads the current OAI configuration and upsert OAI sets accordingly - - - - - - - - - - - - Count records in each OAI set, for each exported metadata format linked to the given oai collection - - - - - - - - - - - - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/publish/jrr_publish_template.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/publish/jrr_publish_template.xml deleted file mode 100644 index 896ade2..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/publish/jrr_publish_template.xml +++ /dev/null @@ -1,183 +0,0 @@ - - -
- - - - - -
- - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - Fetch records from Virtuoso - - - - - - - - - - - - - Feed records into the JRR (registry and catalogue) - - - - - - - - - - - -
diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_bye_template.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_bye_template.xml index 67a5b47..391160f 100644 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_bye_template.xml +++ b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_bye_template.xml @@ -16,10 +16,6 @@ - - - - @@ -65,18 +61,6 @@ - - - - - - Delete from OAI-PMH - - - - - - diff --git a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_hi_CLARIN.xml b/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_hi_CLARIN.xml deleted file mode 100644 index 6d08021..0000000 --- a/dnet-ariadneplus/src/main/resources/eu/dnetlib/bootstrap/profiles/workflows/repo_hi_CLARIN.xml +++ /dev/null @@ -1,180 +0,0 @@ - - -
- - - - - -
- - CLARIN: Aggregate Metadata (X3M) - Collect, transform with X3M, and export metadata for CLARIN - - Aggregate Metadata - Content Provider - - REPO_HI - 20 - - - - - Verify if DS is pending - - - - - - - - - - - Validate DS - - - - - - - Create Workflow - - - - - - - - - - - - - Create native store - - - - - - - - - - - - Create CIDOC store - - - - - - - - - - - - Prepare create index - - - - - - - - - - - Create index - - - - - - - - - Update Workflow Parameters - - - - - - - - - - - - - - - Create Workflow - - - - - - - - - - - - - Create Workflow - - - - - - - - - - - - - - 9 9 9 ? * * - 10080 - - - -
diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/EHRI_sample_record_328.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/EHRI_sample_record_328.xml deleted file mode 100644 index 3fc7826..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/EHRI_sample_record_328.xml +++ /dev/null @@ -1,90 +0,0 @@ - - - - us-005578-irn516886 - - - Romana Primus photograph collection - - - United States Holocaust Memorial Museum -
- 100 Raoul Wallenberg Place, S.W. - DC 20024-2126 - Washington - District of Columbia - US - 202 488 0400 - 202-479-9726 - http://www.ushmm.org/ - archives@ushmm.org - United States -
-
- - -

This encoded description is derived from structured data provided to EHRI by a partner institution but may differ in structure and/or content from its source. The collection holding institution considers this description as an accurate reflection of the archival holdings to which it refers at the moment of data transfer.

-
-
-
- - This file was exported automatically from the EHRI database administration tool and represents a work-in-progress. - 2017-06-01T16:15:08.688+01:00 - - - English - - - - - 2014-12-19T16:12:54.402Z - These files were provided by the United States Holocaust Memorial Museum to EHRI on 2014-11-21. - - [ingest] - - -
- - - irn516886 - Romana Primus photograph collection - 1946-1947 - - United States Holocaust Memorial Museum - - - -

-
- -

-
- -

-
- -

-
- -

-
- -

-
- - Refugees--Germany--1940-1950. - Refugee camps--Germany--1940-1950. - - - Photographs. - - - Kirszenbaum, Halina Grauman. - Brechner, Dosia Grinburg. - Weinreich, Hela. - Strochlitz, Rose Grinburg. - Strochlitz, Sigmund. - Primus, Romana Strochlitz. - -
-
\ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex1.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex1.xml deleted file mode 100644 index 6d349d5..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex1.xml +++ /dev/null @@ -1,288 +0,0 @@ - - - - cendari_____::000298d8a61b4f7b0fe5c7fd3d8c4c9c - 223141 - 2018-10-11T18:17:36.268+02:00 - cendari_____ - CENDARI - api_________::ariadneplus___::cendari::autori - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - BISLAM - CALMA - - - - - - - file%3A%2F%2F%2Fvar%2Flib%2Fariadneplus-data%2Fcendari%2FCAutori - - - - - - - - diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex2.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex2.xml deleted file mode 100644 index 2c17953..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_author_ex2.xml +++ /dev/null @@ -1,43 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - BISLAM - CALMA - MEL - - - diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_manoscritto.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_manoscritto.xml deleted file mode 100644 index 731c70e..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_manoscritto.xml +++ /dev/null @@ -1,112 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - MEL - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_testi1.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_testi1.xml deleted file mode 100644 index 5c72453..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/cendari_testi1.xml +++ /dev/null @@ -1,187 +0,0 @@ - - - - - - - - - - - - - - - - - - - - - LIO - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/culturaItalia_record.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/culturaItalia_record.xml deleted file mode 100644 index f98a87b..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/culturaItalia_record.xml +++ /dev/null @@ -1,212 +0,0 @@ - - - - cultitalia__::001190b56346cf563fdec1ccadc7b89e - oai:culturaitalia.it:oai:culturaitalia.it:museiditalia-coll_91 - 2017-08-10T17:21:47.365+02:00 - cultitalia__ - Cultura Italia - api_________::ariadneplus___::culturaitalia::musei - oai:culturaitalia.it:oai:culturaitalia.it:museiditalia-coll_91 - 2017-03-07T12:04:37Z - museiditalia_opere - museiditalia_coll - - - - coll_91 - Collezione di telecomunicazioni del Museo Nazionale della Scienza e della Tecnologia "Leonardo da Vinci" - La raccolta si compone di oltre 1300 beni, dal 1850 ad oggi, ed è costituita da strumenti ed apparati di tipo storico e didattico per la comunicazione a distanza, provenienti da enti pubblici, università, aziende e privati cittadini. Fanno parte di questa collezione cimeli rari come quelli marconiani e importanti riproduzioni storiche (come i telefoni di Meucci, il pantelegrafo di Caselli), impianti o parti di apparati pubblici e privati, dispositivi utilizzati in laboratori specialistici e prodotti industriali di largo consumo. - Nell'ambito del Sistema Informativo Regionale Beni Culturali sono state realizzate 148 schede di catalogo. - La raccolta di telecomunicazioni nei primi anni di vita del Museo, 1953-1958, contava già più di cento importanti beni provenienti da istituti pubblici e privati e da privati cittadini (CNR, l'allora Ministero delle Poste e Telecomunicazioni, la Società Radiomattima, la Compagnia Marconi, la Magneti Marelli, o il cavalier Donner Flori). Nel 1971, in occasione dell'inaugurazione di una nuova sala dedicata alle telecomunicazioni, la raccolta si arricchì di beni aventi una più ampia apertura verso le tecnologie della rete, grazie anche alle collaborazioni con società come la SIT-Siemens, la SIP, la Sirti, la Telettra. La raccolta è costantemente incrementata e aggiornata sulle nuove tecnologie anche in relazione alle nuove sezione espositive di Telegrafo e telefono, Radio (2005) e Televisione (2008). - Museo Nazionale della Scienza e della Tecnologia "Leonardo da Vinci", Via San Vittore, 21 - Milano (MI), Italia - proprietà privata - name=Milano; year=2001; code=015146 - 1953 post; XX/ XXI - start=1953; end=1953 - Collezioni - Collection - oai:culturaitalia.it:museiditalia-mus_4467 - oai:culturaitalia.it:museiditalia-work_7244 - oai:culturaitalia.it:museiditalia-work_7245 - oai:culturaitalia.it:museiditalia-work_7246 - oai:culturaitalia.it:museiditalia-work_7247 - oai:culturaitalia.it:museiditalia-work_7248 - oai:culturaitalia.it:museiditalia-work_7249 - oai:culturaitalia.it:museiditalia-work_7250 - oai:culturaitalia.it:museiditalia-work_7251 - oai:culturaitalia.it:museiditalia-work_7252 - oai:culturaitalia.it:museiditalia-work_7253 - oai:culturaitalia.it:museiditalia-work_7254 - oai:culturaitalia.it:museiditalia-work_7255 - oai:culturaitalia.it:museiditalia-work_7256 - oai:culturaitalia.it:museiditalia-work_7257 - oai:culturaitalia.it:museiditalia-work_7258 - oai:culturaitalia.it:museiditalia-work_7259 - oai:culturaitalia.it:museiditalia-work_7260 - oai:culturaitalia.it:museiditalia-work_7261 - oai:culturaitalia.it:museiditalia-work_7262 - oai:culturaitalia.it:museiditalia-work_7263 - oai:culturaitalia.it:museiditalia-work_7264 - oai:culturaitalia.it:museiditalia-work_7265 - oai:culturaitalia.it:museiditalia-work_7266 - oai:culturaitalia.it:museiditalia-work_7267 - oai:culturaitalia.it:museiditalia-work_7268 - oai:culturaitalia.it:museiditalia-work_7269 - oai:culturaitalia.it:museiditalia-work_7270 - oai:culturaitalia.it:museiditalia-work_7271 - oai:culturaitalia.it:museiditalia-work_7272 - oai:culturaitalia.it:museiditalia-work_7273 - oai:culturaitalia.it:museiditalia-work_7274 - oai:culturaitalia.it:museiditalia-work_7275 - oai:culturaitalia.it:museiditalia-work_7276 - oai:culturaitalia.it:museiditalia-work_7277 - oai:culturaitalia.it:museiditalia-work_7278 - oai:culturaitalia.it:museiditalia-work_7279 - oai:culturaitalia.it:museiditalia-work_7280 - oai:culturaitalia.it:museiditalia-work_7281 - oai:culturaitalia.it:museiditalia-work_7282 - oai:culturaitalia.it:museiditalia-work_7283 - oai:culturaitalia.it:museiditalia-work_7284 - oai:culturaitalia.it:museiditalia-work_7285 - oai:culturaitalia.it:museiditalia-work_7286 - oai:culturaitalia.it:museiditalia-work_7287 - oai:culturaitalia.it:museiditalia-work_7288 - oai:culturaitalia.it:museiditalia-work_7289 - oai:culturaitalia.it:museiditalia-work_7290 - oai:culturaitalia.it:museiditalia-work_7291 - oai:culturaitalia.it:museiditalia-work_7292 - oai:culturaitalia.it:museiditalia-work_7293 - oai:culturaitalia.it:museiditalia-work_7294 - oai:culturaitalia.it:museiditalia-work_7295 - oai:culturaitalia.it:museiditalia-work_7296 - oai:culturaitalia.it:museiditalia-work_7297 - oai:culturaitalia.it:museiditalia-work_7298 - oai:culturaitalia.it:museiditalia-work_7299 - oai:culturaitalia.it:museiditalia-work_7300 - oai:culturaitalia.it:museiditalia-work_7301 - oai:culturaitalia.it:museiditalia-work_7302 - oai:culturaitalia.it:museiditalia-work_7303 - oai:culturaitalia.it:museiditalia-work_7304 - oai:culturaitalia.it:museiditalia-work_7305 - oai:culturaitalia.it:museiditalia-work_7306 - oai:culturaitalia.it:museiditalia-work_7307 - oai:culturaitalia.it:museiditalia-work_7308 - oai:culturaitalia.it:museiditalia-work_7309 - oai:culturaitalia.it:museiditalia-work_7310 - oai:culturaitalia.it:museiditalia-work_7311 - oai:culturaitalia.it:museiditalia-work_7312 - oai:culturaitalia.it:museiditalia-work_7313 - oai:culturaitalia.it:museiditalia-work_7314 - oai:culturaitalia.it:museiditalia-work_7315 - oai:culturaitalia.it:museiditalia-work_7316 - oai:culturaitalia.it:museiditalia-work_7317 - oai:culturaitalia.it:museiditalia-work_7318 - oai:culturaitalia.it:museiditalia-work_7319 - oai:culturaitalia.it:museiditalia-work_7320 - oai:culturaitalia.it:museiditalia-work_7321 - oai:culturaitalia.it:museiditalia-work_7322 - oai:culturaitalia.it:museiditalia-work_7323 - oai:culturaitalia.it:museiditalia-work_7324 - oai:culturaitalia.it:museiditalia-work_7325 - oai:culturaitalia.it:museiditalia-work_7326 - oai:culturaitalia.it:museiditalia-work_7327 - oai:culturaitalia.it:museiditalia-work_7328 - oai:culturaitalia.it:museiditalia-work_7329 - oai:culturaitalia.it:museiditalia-work_7330 - oai:culturaitalia.it:museiditalia-work_7331 - oai:culturaitalia.it:museiditalia-work_7332 - oai:culturaitalia.it:museiditalia-work_7333 - oai:culturaitalia.it:museiditalia-work_7334 - oai:culturaitalia.it:museiditalia-work_7335 - oai:culturaitalia.it:museiditalia-work_7336 - oai:culturaitalia.it:museiditalia-work_7337 - oai:culturaitalia.it:museiditalia-work_7338 - oai:culturaitalia.it:museiditalia-work_7339 - oai:culturaitalia.it:museiditalia-work_7340 - oai:culturaitalia.it:museiditalia-work_7341 - oai:culturaitalia.it:museiditalia-work_7342 - oai:culturaitalia.it:museiditalia-work_7343 - oai:culturaitalia.it:museiditalia-work_7344 - oai:culturaitalia.it:museiditalia-work_7345 - oai:culturaitalia.it:museiditalia-work_7346 - oai:culturaitalia.it:museiditalia-work_7347 - oai:culturaitalia.it:museiditalia-work_7348 - oai:culturaitalia.it:museiditalia-work_7349 - oai:culturaitalia.it:museiditalia-work_7350 - oai:culturaitalia.it:museiditalia-work_7351 - oai:culturaitalia.it:museiditalia-work_7352 - oai:culturaitalia.it:museiditalia-work_7353 - oai:culturaitalia.it:museiditalia-work_7354 - oai:culturaitalia.it:museiditalia-work_7355 - oai:culturaitalia.it:museiditalia-work_7356 - oai:culturaitalia.it:museiditalia-work_7357 - oai:culturaitalia.it:museiditalia-work_7358 - oai:culturaitalia.it:museiditalia-work_7359 - oai:culturaitalia.it:museiditalia-work_7360 - oai:culturaitalia.it:museiditalia-work_7361 - oai:culturaitalia.it:museiditalia-work_7362 - oai:culturaitalia.it:museiditalia-work_7363 - oai:culturaitalia.it:museiditalia-work_7364 - oai:culturaitalia.it:museiditalia-work_7365 - oai:culturaitalia.it:museiditalia-work_7366 - oai:culturaitalia.it:museiditalia-work_7367 - oai:culturaitalia.it:museiditalia-work_7368 - oai:culturaitalia.it:museiditalia-work_7369 - oai:culturaitalia.it:museiditalia-work_7370 - oai:culturaitalia.it:museiditalia-work_7371 - oai:culturaitalia.it:museiditalia-work_7372 - oai:culturaitalia.it:museiditalia-work_7373 - oai:culturaitalia.it:museiditalia-work_7374 - oai:culturaitalia.it:museiditalia-work_7375 - oai:culturaitalia.it:museiditalia-work_7376 - oai:culturaitalia.it:museiditalia-work_7377 - oai:culturaitalia.it:museiditalia-work_7378 - oai:culturaitalia.it:museiditalia-work_7379 - oai:culturaitalia.it:museiditalia-work_7380 - oai:culturaitalia.it:museiditalia-work_7381 - oai:culturaitalia.it:museiditalia-work_7382 - oai:culturaitalia.it:museiditalia-work_7383 - oai:culturaitalia.it:museiditalia-work_7384 - oai:culturaitalia.it:museiditalia-work_7385 - oai:culturaitalia.it:museiditalia-work_7386 - oai:culturaitalia.it:museiditalia-work_7387 - oai:culturaitalia.it:museiditalia-work_7388 - oai:culturaitalia.it:museiditalia-work_7389 - oai:culturaitalia.it:museiditalia-work_7390 - scheda SIRBeC COL: COL-ST010-0000002 - http://194.242.241.163/fedora/objects/coll:91/datastreams/MM258501/content - title=visualizza il file Mets; URL=fedora/objects/coll:91/datastreams/export/content - - - - - - http%3A%2F%2Fwww.culturaitalia.it%2FoaiProviderCI%2FOAIHandler - oai:culturaitalia.it:oai:culturaitalia.it:museiditalia-coll_91 - 2017-03-07T12:04:37Z - - - - - - diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah.xml deleted file mode 100644 index 01ee062..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah.xml +++ /dev/null @@ -1,97 +0,0 @@ - - - - dariah_gr___::35cf8659cfcb13224cbd47863a34fc58 - 796 - 2017-09-20T12:03:30.827+02:00 - dariah_gr___ - DARIAH-GR - api_________::ariadneplus___::dariahGR::oai - 796 - 2016-11-09T20:21:34Z - - - - - Το εραλδικό φαινόμενο, η πρώτη εμφάνιση του οποίου εντοπίζεται στη Δυτική και Κεντρική Ευρώπη, στο δεύτερο τέταρτο του 12ου αιώνα, παρουσιάζεται στον Ελλαδικό χώρο καθυστερημένα και διαδίδεται σε μικρότερη έκταση. - Στην Ελλάδα, τα πρώτα εραλδικά κατάλοιπα, όπως τα εντοπίζει η ιστορική έρευνα, χρονολογούνται από τον 14ο αιώνα, για να πυκνώσουν αποφασιστικά τον 15ο και 16ο, όταν το φαινόμενο φθάνει στη μεγαλύτερη ακμή του, και να συνεχίσουν με μια ύφεση, παραμένοντας ωστόσο σε ένα αξιόλογο επίπεδο, μέχρι τα τέλη του 19ου αιώνα. - Το Ινστιτούτο Νεοελληνικών Ερευνών αναγνωρίζοντας τη σημασία της μελέτης του φαινομένου αυτού για τη νεότερη ελληνική ιστορία και την ανάγκη να υπερκεραστεί το στάδιο της ερασιτεχνικής προσέγγισής του, έχει εντάξει στις ερευνητικές του δραστηριότητες τη συστηματική αναζήτηση, καταγραφή, φωτογράφηση και ταξινόμησή τους, με στόχο τη συγκρότηση ενός αρχείου των εραλδικών μνημείων στην Ελλάδα. - Τρεις είναι οι βασικές γεωγραφικές περιοχές με τη μεγαλύτερη συμβολή: - οι Λατινοκρατούμενες Κυκλάδες, - τα Δωδεκάνησα των Ιωαννιτών ιπποτών και - η Βενετική κυριαρχία κυρίως στην Κρήτη, τα Επτάνησα και την Πελοπόννησο - - Δευτερεύουσες συμβολές προκύπτουν από τη Γενοβέζικη παρουσία (κυρίως στο Βορειοανατολικό Αιγαίο), την Καθολική εκκλησία (που διασταυρώνει όλα τα προηγούμενα) και τέλος τη μικρή ομάδα των Φαναριωτών. - Στην παρούσα βάση παρουσιάζονται ενδεικτικά 443 εγγραφές. Από αυτές, οι 147 χρονολογούνται μεταξύ του 13ου-15ου αιώνα, οι 170 από τον 16ο-17ο αιώνα, οι 105 από τον 18ο-19ο αιώνα, ενώ 21 προέρχονται από τον 20ό αιώνα. Χωροταξικά ο μεγάλος όγκος προέρχεται από τα νησιά του Αιγαίου (258 εγγραφές), ενώ εκπροσωπούνται επίσης η Κρήτη (85 εγγραφές), τα Επτάνησα (44 εγγραφές), η Στερεά Ελλάδα (38 εγγραφές) και η Πελοπόννησος (18 εγγραφές). Κάθε εγγραφή περιλαμβάνει τη θέση στην οποία βρίσκεται το μνημείο, την ταύτιση και τη χρονολόγησή του, ένα σύντομο ιστορικό σημείωμα, μια ενδεικτική βιβλιογραφία και μία πρόσφατη απεικόνισή του. - Η μεταγραφή των ελληνικών χαρακτήρων σε λατινικούς έγινε με βάση το Ελληνικό Πρότυπο του ΕΛΟΤ 743, 2η έκδοση. - - - - Heraldic Database of Greece - - http://pandektis.ekt.gr/pandektis/handle/10442/1 - 0 - - Εθνικό Ίδρυμα Ερευνών - - Δεν υπάρχουν περιορισμοί πνευματικών δικαιωμάτων σε ό,τι αφορά τα ιστορικά στοιχεία που εμφανίζονται στις εγγραφές. Σε ό,τι αφορά τις απεικονίσεις, τα πνευματικά δικαιώματα ανήκουν στο Ινστιτούτο Νεοελληνικών Ερευνών του ΕΙΕ και, συνεπώς, απαιτείται η άδειά του για την αντιγραφή ή την περαιτέρω χρήση τους. - 0 - Νεότερα μνημεία, Οικογένειες, Νεότερη Κοινωνική Ιστορία, Εραλδική - Αρχείο Εραλδικών Μνημείων του Ελλαδικού Χώρου - - Συλλογή - - 0 - 0 - 0 - - 443 εγγραφές - - - - coll:796 - - Πανδέκτης: Ψηφιακός Θησαυρός Πρωτογενών Τεκμηρίων Ελληνικής Ιστορίας και Πολιτισμού - - - - - - - - Ελληνικά, Νέα (1453-) - - - Αγγλικά - - - Εθνικό Ίδρυμα Ερευνών - - - Αιγαίο - - - Κρήτη - - - Επτάνησα - - - Στερεά Ελλάδα - - - Πελοπόννησος - - - - - - - http%3A%2F%2Fregistry-dyas.imis.athena-innovation.gr%3A8080%2Fdyas - 796 - 2016-11-09T20:21:34Z - - - - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah2.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah2.xml deleted file mode 100644 index 5092477..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah2.xml +++ /dev/null @@ -1,81 +0,0 @@ - - - - dariah_gr___::000871c1fc726f0b52dc86a4eeb027de - 4612 - 2017-11-03T16:02:26.229+01:00 - dariah_gr___ - DARIAH-GR - api_________::ariadneplus___::dariahGR::oai - 4612 - 2016-11-09T20:24:58Z - - - - - Η συλλογή περιλαμβάνει αντικείμενα που χρονολογούνται από την νεολιθική ως και τη ρωμαϊκή εποχή. Ξεχωρίζουν σημαντικά έργα της αρχαίας ελληνικής γλυπτικής, όπως το ακέραιο μαρμάρινο άγαλμα της Γοργούς, δύο μαρμάρινες ανάγλυφες πλάκες από το Ηρώο του Αρχιλόχου, μαρμάρινο κολοσσικό άγαλμα Αρτέμιδας από το ιερό του Απόλλωνα Δηλίου και της Αρτέμιδας Δηλίας, στο Δήλιο της Πάρου. - - - Archaeological Museum of Paros Collection - - 1390 - - Αρχαιολογικό Μουσείο Πάρου - - 0 - Προϊστορική Αρχαιολογία, Κλασική Aρχαιολογία, Γλυπτική, Επιγραφική, Μικροτεχνία, - Συλλογή Αρχαιολογικού Μουσείου Πάρου - - Συλλογή - - 0 - 0 - 0 - - - - - - coll:4612 - - - - - - μάρμαρο - - - πηλός - - - - Ελληνικά, Νέα (1453-) - - - Αρχαιολογικό Μουσείο Πάρου - - - - Πάρος - - - - - - - http%3A%2F%2Fregistry-dyas.imis.athena-innovation.gr%3A8080%2Fdyas - 4612 - 2016-11-09T20:24:58Z - - - - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah_orig.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah_orig.xml deleted file mode 100644 index 950ce3b..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/dariah_orig.xml +++ /dev/null @@ -1,58 +0,0 @@ - - -
- 4612 - 2016-11-09T20:24:58Z -
- - - - Η συλλογή περιλαμβάνει αντικείμενα που χρονολογούνται από την νεολιθική ως και τη ρωμαϊκή εποχή. Ξεχωρίζουν σημαντικά έργα της αρχαίας ελληνικής γλυπτικής, όπως το ακέραιο μαρμάρινο άγαλμα της Γοργούς, δύο μαρμάρινες ανάγλυφες πλάκες από το Ηρώο του Αρχιλόχου, μαρμάρινο κολοσσικό άγαλμα Αρτέμιδας από το ιερό του Απόλλωνα Δηλίου και της Αρτέμιδας Δηλίας, στο Δήλιο της Πάρου. - - - Archaeological Museum of Paros Collection - - 1390 - - Αρχαιολογικό Μουσείο Πάρου - - 0 - Προϊστορική Αρχαιολογία, Κλασική Aρχαιολογία, Γλυπτική, Επιγραφική, Μικροτεχνία, - Συλλογή Αρχαιολογικού Μουσείου Πάρου - - Συλλογή - - 0 - 0 - 0 - - - - - - coll:4612 - - - - - - μάρμαρο - - - πηλός - - - - Ελληνικά, Νέα (1453-) - - - Αρχαιολογικό Μουσείο Πάρου - - - - Πάρος - - - -
- diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/ehri_test.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/ehri_test.xml deleted file mode 100644 index 62bd7cb..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/ehri_test.xml +++ /dev/null @@ -1,100 +0,0 @@ - - - us-005578-irn516886 - - - Romana Primus photograph collection - - - United States Holocaust Memorial Museum -
- 100 Raoul Wallenberg Place, S.W. - DC 20024-2126 - Washington - District of Columbia - US - 202 488 0400 - 202-479-9726 - http://www.ushmm.org/ - archives@ushmm.org - United States -
-
- - -

This encoded description is derived from structured data provided to EHRI by a partner institution but may differ in structure and/or content from its source. The collection holding institution considers this description as an accurate reflection of the archival holdings to which it refers at the moment of data transfer.

-
-
-
- - This file was exported automatically from the EHRI database administration tool and represents a work-in-progress. - 2017-05-13T09:25:31.407+01:00 - - - English - - - - - 2014-12-19T16:12:54.402Z - These files were provided by the United States Holocaust Memorial Museum to EHRI on 2014-11-21. - - [ingest] - - - -
- - - irn516886 - Romana Primus photograph collection - 1946-1947 - - United States Holocaust Memorial Museum - - - -

The collection consists of four photographs of Romana Strochlitz Primus as a baby, her parents, Sigmund and Ruzka (Rose) Grinburg Strochlitz, and other refugees at the Bergen-Belsen displaced persons camp in Germany after World War II.

-
- -

No restrictions on access

-
- -

No restrictions on use

-
- -

Accession number: 1999.18

-
- -

The collection was donated to the United States Holocaust Memorial Museum by Romana Strochlitz Primus in 1999.

-
- -

Record type: Document

-
- - Refugees--Germany--1940-1950. - Refugee camps--Germany--1940-1950. - - - Kirszenbaum, Halina Grauman. - Brechner, Dosia Grinburg. - Weinreich, Hela. - Strochlitz, Rose Grinburg. - Strochlitz, Sigmund. - Primus, Romana Strochlitz. - - - Photographs. - -
-
- - diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/metashare.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/metashare.xml deleted file mode 100644 index 6c2de08..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/metashare.xml +++ /dev/null @@ -1,297 +0,0 @@ - - - - Strongly Comparable and Aligned Legal News EN-FR-RO News Corpus - This corpus is a collection of strongly comparable English, French and Romanian documents collected from http://ec.europa.eu/ website that are sentence split, POS tagged, lemmatized and chunked and that are also sentence aligned using Moore's sentence aligner (http://research.microsoft.com/pubs/68886/sent-align2-amta-final.pdf). - NOT_DEFINED_FOR_V2 - RACAIEnFrRoNewsCorpus - - - available-restrictedUse - - MSCommons-BY-NC-ND - academic-nonCommercialUse - attribution - informLicensor - noRedistribution - accessibleThroughInterface - downloadable - Please cite this paper: "Radu Ion, Dan Tufiş, Tiberiu Boroş, Alexandru Ceauşu, and Dan Ştefănescu. On-Line Compilation of Comparable Corpora and their Evaluation. In Marko Tadić, Mila Dimitrova-Vulchanova, and Svetla Koeva (eds.), Proceedings of The 7th International Conference Formal Approaches to South Slavic and Balkan Languages (FASSBL-7), pp. 29—34, Croatian Language Technologies Society – Faculty of Humanities and Social Sciences, Zagreb, Croatia, October 2010. ISBN: 978-953-55375-2-6." - - - Research Institute for Artificial Intelligence, Romanian Academy - RACAI - ICIA - NLP Group - - office@racai.ro - http://www.racai.ro/ -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, București, România, 050711
- 050711 - Bucharest - Romania - 0040 21 3188103 - 0040 21 3188142 -
-
-
- - - Research Institute for Artificial Intelligence, Romanian Academy - RACAI - ICIA - NLP Group - - office@racai.ro - http://www.racai.ro/ -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, București, România, 050711
- 050711 - Bucharest - Romania - 0040 21 3188103 - 0040 21 3188142 -
-
-
- academic - commercial -
- - - Research Institute for Artificial Intelligence, Romanian Academy - RACAI - ICIA - NLP Group - - office@racai.ro - http://www.racai.ro/ -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, București, România, 050711
- 050711 - Bucharest - Romania - 0040 21 3188103 - 0040 21 3188142 -
-
-
-
- - Ion - Radu - - radu@racai.ro - http://www.racai.ro/~radu -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
- senior researcher, 3rd grade - - "Mihai Drăgănescu" Research Institute for Artificial Intelligence of the Romanian Academy - RACAI - NLP Group - - office@racai.ro - http://www.racai.ro -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
-
-
- - 2012-12-18 - - Ion - Radu - - radu@racai.ro - http://www.racai.ro/~radu -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
- senior researcher, 3rd grade - - "Mihai Drăgănescu" Research Institute for Artificial Intelligence of the Romanian Academy - RACAI - NLP Group - - office@racai.ro - http://www.racai.ro -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
-
-
- METANET4U - 3.0 - English - en - 2012-12-18 -
- - true - formal - automatic - Parsed for XCES conformance. - full - - - Ion - Radu - - radu@racai.ro - http://www.racai.ro/~radu -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
- senior researcher, 3rd grade - - "Mihai Drăgănescu" Research Institute for Artificial Intelligence of the Romanian Academy - RACAI - NLP Group - - office@racai.ro - http://www.racai.ro -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
-
-
-
-
- - - - manual - Strongly Comparable and Aligned Legal News EN-FR-RO News Corpus - Radu Ion - http://ws.racai.ro:9191/narratives/batch3/EnFrRoSentenceAlignedCorpus.pdf - parallel corpus, English, Romanian, French, POS-tagged, lemmatized, chunked - English - en - - - manual - - - - - Ion - Radu - - radu@racai.ro - http://www.racai.ro/~radu -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
- senior researcher, 3rd grade - - "Mihai Drăgănescu" Research Institute for Artificial Intelligence of the Romanian Academy - RACAI - NLP Group - - office@racai.ro - http://www.racai.ro -
Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310
- 050711 - București - România - 0040 21 3188103 - 0040 21 3188142 -
-
-
-
-
- - - corpus - - - text - - multilingual - comparable - A parallel sub-corpus is extracted. - - - en - English - - 1848 - files - - - - fr - French - - 1809 - files - - - - ro - Romanian - - 966 - files - - - - writtenLanguage - - - 4623 - files - - - text/xml - - - UTF-8 - - - Legal news - other - - - Years 2010-2011 - - - automatic - - - - - -
\ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304736.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304736.xml deleted file mode 100755 index cfcbaac..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304736.xml +++ /dev/null @@ -1,40 +0,0 @@ - - - - - - PIT - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - No title - Pre 1350 coal pit - 2004-09-15 00:00:00.0 - 2004-09-15 00:00:00.0 - 977352 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=977352 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1066 - 1540 - - - ENGLAND - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304736 - pits (earthworks)http://vocab.getty.edu/aat/300008027 - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304737.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304737.xml deleted file mode 100755 index a5cc61d..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304737.xml +++ /dev/null @@ -1,43 +0,0 @@ - - - - - - TERRACED HOUSE - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - 19 QUEEN ANNES GROVE, EALING - TERRACED HOUSE - 19 QUEEN ANNES GROVE, EALING - 1999-05-06 00:00:00.0 - 1999-05-06 00:00:00.0 - 637688 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=637688 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1540 - 1901 - - - 19 QUEEN ANNES GROVE - 51.49648 - -.25671 - England - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304737 - - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304738.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304738.xml deleted file mode 100755 index 6ca3fd9..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304738.xml +++ /dev/null @@ -1,42 +0,0 @@ - - - - - - WINDMILL - - - - Archaeology Data Service - Organization - - - Sustainability Group, Shropshire County Council - Organization - - Crudgington Windmill - Windmill <1> - 2002-11-20 00:00:00.0 - 2002-11-20 00:00:00.0 - 67142 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=67142 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1540 - 1901 - - - 52.758881 - -2.552782 - England - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304738 - windmillshttp://vocab.getty.edu/aat/300006273 - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304739.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304739.xml deleted file mode 100755 index e159b84..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304739.xml +++ /dev/null @@ -1,60 +0,0 @@ - - - - - - EARTHWORK - - - - - FISHPOND - - - - - MANOR HOUSE - - - - - MOAT - - - - - TRACKWAY - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - MOAT FARM - Medieval moated manor house. House replaced by a 19th century farmhouse. Other features include fishponds, trackways and field system. - 2004-09-15 00:00:00.0 - 2004-09-15 00:00:00.0 - 1055485 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=1055485 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1066 - 1540 - - - ENGLAND - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304739 - earthworks (engineering works)http://vocab.getty.edu/aat/300008020fishpondshttp://vocab.getty.edu/aat/300008689manor houseshttp://vocab.getty.edu/aat/300005579 - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304740.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304740.xml deleted file mode 100755 index 719fb0c..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304740.xml +++ /dev/null @@ -1,57 +0,0 @@ - - - - - - COUNTRY HOUSE - - - - - DEMOLISHED BUILDING - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - STOKE PARK HOUSE - Country house constructed between 1629 and 1635 possibly by Inigo Jones. the principal south front of the house was three storeys above a basement. The two principal storeys were defined by a giant Ionic order supporting an entablature. Alteratins were carried out after 1786 to deisgns by Levison Vernon. The house was destroyed by a fire in 1886. - 2004-09-15 00:00:00.0 - 2004-09-15 00:00:00.0 - 1052615 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=1052615 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1540 - 1901 - - - 1886 - 1886 - - - 1786 - 1786 - - - 1629 - 1635 - - - ENGLAND - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304740 - - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304741.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304741.xml deleted file mode 100755 index a82cc0b..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304741.xml +++ /dev/null @@ -1,44 +0,0 @@ - - - - - - BUILDING - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - BIRMINGHAM MIDLAND INSTITUTE (FY THE BIRMINGHAM LIBRARY) - 1899 - 2004-09-15 00:00:00.0 - 2004-09-15 00:00:00.0 - 1046309 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=1046309 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - 1540 - 1901 - - - 1899 - 1899 - - - ENGLAND - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304741 - buildings (structures)http://vocab.getty.edu/aat/300004792 - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304742.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304742.xml deleted file mode 100755 index 5d29d7d..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/new-10304742.xml +++ /dev/null @@ -1,50 +0,0 @@ - - - - - - FINDSPOT - - - - - RAPIER - - - - - SWORD - - - - Archaeology Data Service - Organization - - - Historic England - Organization - - No title - Bronze age rapier - 2004-09-15 00:00:00.0 - 2004-09-15 00:00:00.0 - 1050544 - en - http://archaeologydataservice.ac.uk/archsearch/record.jsf?titleId=1050544 - http://archaeologydataservice.ac.uk/advice/termsOfUseAndAccess - ADS Terms and Conditions - - -2600 - -700 - - - ENGLAND - EPSG:27700 - - Sites and monuments databases or inventories - - http://registry.ariadne-infrastructure.eu/collection/22721290 - http://registry.ariadne-infrastructure.eu/dataset/10304742 - rapiershttp://vocab.getty.edu/aat/300037085swordshttp://vocab.getty.edu/aat/300037048archaeological siteshttp://vocab.getty.edu/aat/300000810 - - \ No newline at end of file diff --git a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/wp8.xml b/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/wp8.xml deleted file mode 100644 index 3dc937d..0000000 --- a/dnet-ariadneplus/src/test/resources/eu/dnetlib/x3m/wp8.xml +++ /dev/null @@ -1,61 +0,0 @@ - - Alliance Permanent Access to the Records of Science in Europe Network - APARSEN - http://www.alliancepermanentaccess.org/ - KNAW-DANS, PIN - Projects - Europe - - - - - - - - - - - - - Yes - - - - - - - - - - - - - Yes - - - Yes - Yes - - - - - Yes - - - Yes - Yes - - Yes - - - KNAW-DANS, PIN - - director@alliancepermanentaccess.org - - - - Closed - Yes - - - \ No newline at end of file