diff --git a/.gitattributes b/.gitattributes
index d9210ecdace545fca1a788ab6423de7c6a55f578..5259e5c7e355d3d7bdc0a52825f00753d6994517 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -4,3 +4,4 @@ data/AB/1892/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1893/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1891/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1892/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1893/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/90d0c14f67804d9694908085fc4ac36c_python.cwl b/.renku/workflow/90d0c14f67804d9694908085fc4ac36c_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..b2814e9594921b8dfdd9e93c3d6d3f0c15e32af8
--- /dev/null
+++ b/.renku/workflow/90d0c14f67804d9694908085fc4ac36c_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/1893/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1893/02_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/1893
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1893/02_extractedxml.tar.gz b/data/AB/1893/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f3e0901641beb5f1f7f5cce7f065f7ab7ccd05ff
--- /dev/null
+++ b/data/AB/1893/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcd3bfa25b8e7cb1906cd0072b999f186ea7994632acf7c5f0f4cd38dc48d43
+size 47034427