Merge pull request #107 from emt-project/105-add-script-to-download-i…

…mages-from-transkribus 105 add script to download images from transkribus
emt-project · Dec 10, 2024 · 62e15dd · 62e15dd
2 parents 950eed5 + 7797862
commit 62e15dd
Show file tree

Hide file tree

Showing 5 changed files with 24 additions and 6 deletions.
diff --git a/arche__filechecker.sh b/arche__filechecker.sh
@@ -6,7 +6,7 @@ docker run \
   --rm \
   --network="host" \
   -v ${PWD}/fc_out:/reports \
-  -v ${PWD}/to_ingest:/data \
+  -v ${PWD}/img:/data \
   --entrypoint arche-filechecker \
   acdhch/arche-ingest \
   --overwrite --skipWarnings --html /data /reports

diff --git a/arche__ingest_binaries.sh b/arche__ingest_binaries.sh
@@ -2,7 +2,7 @@
 
 echo "ingest binaries for ${TOPCOLID} into ${ARCHE}"
 docker run --rm \
-  -v ${PWD}/to_ingest:/data \
+  -v ${PWD}/img:/data \
   --network="host" \
   --entrypoint arche-import-binary \
   acdhch/arche-ingest \

diff --git a/arche_seed_files/arche_constants.ttl b/arche_seed_files/arche_constants.ttl
@@ -80,7 +80,7 @@
     acdh:hasCoverageEndDate "1716-01-31"^^xsd:date ;
     acdh:hasLifeCycleStatus <https://vocabs.acdh.oeaw.ac.at/archelifecyclestatus/active> ;
     acdh:hasCompleteness "Diese Sammlung wird sukzessive erweitert."@de ;
-    acdh:hasUrl "https://emt.acdh-dev.oeaw.ac.at" ;
+    acdh:hasUrl "https://kaiserin-eleonora.oeaw.ac.at/" ;
     acdh:hasSubject "digital edition"@en ;
     acdh:hasSubject "Digitale Edition"@de ;
     acdh:hasSubject "Epistolary correspondence"@en ;

diff --git a/make_arche_rdf.py b/make_arche_rdf.py
@@ -14,7 +14,7 @@
 g = Graph().parse("arche_seed_files/arche_constants.ttl")
 g_repo_objects = Graph().parse("arche_seed_files/repo_objects_constants.ttl")
 TOP_COL_URI = URIRef("https://id.acdh.oeaw.ac.at/emt")
-APP_URL = "https://emt.acdh-dev.oeaw.ac.at/"
+APP_URL = "https://kaiserin-eleonora.oeaw.ac.at/"
 
 ACDH = Namespace("https://vocabs.acdh.oeaw.ac.at/schema#")
 COLS = [ACDH["TopCollection"], ACDH["Collection"], ACDH["Resource"]]
@@ -49,6 +49,15 @@
     cur_doc_uri = URIRef(f"{TOP_COL_URI}/{cur_doc_id}")
     g.add((cur_doc_uri, RDF.type, ACDH["Resource"]))
     g.add((cur_doc_uri, ACDH["isPartOf"], cur_col_uri))
+    g.add(
+        (
+            cur_doc_uri,
+            ACDH["hasUrl"],
+            Literal(
+                f"{APP_URL}{cur_doc_id.replace(".xml", ".html")}", datatype=XSD.anyURI
+            ),
+        )
+    )
     g.add(
         (
             cur_doc_uri,
@@ -169,7 +178,13 @@
         entity_id = y.xpath("./*[@type='GEONAMES']/text()")[0]
         entity_uri = URIRef(entity_id)
         g.add((entity_uri, RDF.type, ACDH["Place"]))
-        # g.add((entity_uri, ACDH["hasUrl"], Literal(f"{APP_URL}{xml_id}", datatype=XSD.anyURI)))
+        g.add(
+            (
+                entity_uri,
+                ACDH["hasUrl"],
+                Literal(f"{APP_URL}{xml_id}", datatype=XSD.anyURI),
+            )
+        )
         g.add((entity_uri, ACDH["hasTitle"], Literal(entity_title, lang="und")))
         g.add((cur_col_uri, ACDH["hasSpatialCoverage"], entity_uri))
         g.add((cur_doc_uri, ACDH["hasSpatialCoverage"], entity_uri))

diff --git a/make_cmif.py b/make_cmif.py
@@ -59,7 +59,10 @@
         excluded.add(x)
         continue
     item_label = make_entity_label(item_node.xpath("./*[1]")[0])[0]
-    item_gnd = item_node.xpath("./tei:idno[@type='GND']/text()", namespaces=NSMAP)[0]
+    try:
+        item_gnd = item_node.xpath("./tei:idno[@type='GND']/text()", namespaces=NSMAP)[0]
+    except IndexError:
+        item_gnd = False
     item["receiver_label"] = item_label
     item["receiver_gnd"] = item_gnd