diff --git a/.gitattributes b/.gitattributes
index fb683d11ec28eb08338d60542f33742638fb221a..6d46848b367f7b95345325ccd312c79cfd62353d 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -29,3 +29,4 @@ data/AB/1914/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1915/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1916/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1917/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1918/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/21514d64f82c4f7399fd262c1a43df81_python.cwl b/.renku/workflow/21514d64f82c4f7399fd262c1a43df81_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..83676c5d013399834276f14f3f9bab0ce7c81c71
--- /dev/null
+++ b/.renku/workflow/21514d64f82c4f7399fd262c1a43df81_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/1918/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1918/02_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/1918
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1918/02_extractedxml.tar.gz b/data/AB/1918/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..473a7685bba9616ad2dd3e59a44a4df61da03477
--- /dev/null
+++ b/data/AB/1918/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c932a07e67ac349e093d9985b26dc13f842746aa6b2196b3984b84e4485e07ae
+size 72797531