diff --git a/.gitattributes b/.gitattributes
index 7c53f30bd290610d58201555096e2c12b66a5f4d..81a56ee11873ffd22eb714c5c5f82d619e02c57b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -8,3 +8,4 @@ data/AB/1893/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1894/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1895/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1896/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1897/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/725b4b7206f747a7a283396bdd0156e1_python.cwl b/.renku/workflow/725b4b7206f747a7a283396bdd0156e1_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..a77062bc1b39e835fa0b528d14458903e7a61255
--- /dev/null
+++ b/.renku/workflow/725b4b7206f747a7a283396bdd0156e1_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1897/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1897/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1897
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1897/02_extractedxml.tar.gz b/data/AB/1897/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..756d8a65051f54ec6a2ebb4db2113e8508034e87
--- /dev/null
+++ b/data/AB/1897/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7fdccc1ec24d0342a8d010bcc658764d655e33ade687711d4e9647541249b4
+size 96543739