diff --git a/.gitattributes b/.gitattributes
index d544dc1716f4948f29c55f48ee766cfb3ae8b031..d9210ecdace545fca1a788ab6423de7c6a55f578 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -3,3 +3,4 @@ data/AB/1891/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 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
diff --git a/.renku/workflow/e74335e7335143d8ae104b3ac0a260df_python.cwl b/.renku/workflow/e74335e7335143d8ae104b3ac0a260df_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..392727b5e2cadd0512473a31c1616571ce50448a
--- /dev/null
+++ b/.renku/workflow/e74335e7335143d8ae104b3ac0a260df_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/1892/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1892/02_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/1892
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1892/02_extractedxml.tar.gz b/data/AB/1892/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e286b5606fca7f2f433cdfd7a5de8fcda5eb031c
--- /dev/null
+++ b/data/AB/1892/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8207f107ff80317aa64de940930118ffa1b22dd73749cfc22db4f2c5abc018
+size 16471820