diff --git a/.gitattributes b/.gitattributes
index 384156fc293cdb26aefc46f7632806e7fc1a35cc..f891ee52edf6148d4b455bf1fdef96d977417553 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -241,5 +241,12 @@ data/AB/1993/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1994/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1995/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+<<<<<<< HEAD
 data/AB/1975/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1976/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+=======
+data/AB/1974/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1980/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1981/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+>>>>>>> e664070b2412ace18c8f5adafe5e0cf57e0ffce8
+data/AB/1977/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/55db25b9be3e4de8a799064ce8a81038_python.cwl b/.renku/workflow/55db25b9be3e4de8a799064ce8a81038_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..60cb7b6b64955af6734cdc5085559545f9ccc7a2
--- /dev/null
+++ b/.renku/workflow/55db25b9be3e4de8a799064ce8a81038_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/1981/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1981/02_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/1981
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_python.cwl b/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..bfd6aa94e19ac1e78ad7275032beb77935681205
--- /dev/null
+++ b/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_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/1980/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1980/02_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/1980
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/.renku/workflow/ced9d30b55bc41c7aeb714cd1d863012_python.cwl b/.renku/workflow/ced9d30b55bc41c7aeb714cd1d863012_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..67dea3795f9c6c470703e9d053f0f22f80bd26b0
--- /dev/null
+++ b/.renku/workflow/ced9d30b55bc41c7aeb714cd1d863012_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_correctxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1974/02_extractedxml.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1974/04_correctedxml.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/1974
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/.renku/workflow/d4a366e49dc54eee9cc13a47e884b9e5_python.cwl b/.renku/workflow/d4a366e49dc54eee9cc13a47e884b9e5_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..149d732502db5cf746d80f61af9463bc06b12906
--- /dev/null
+++ b/.renku/workflow/d4a366e49dc54eee9cc13a47e884b9e5_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/1977/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1977/02_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/1977
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1974/04_correctedxml.tar.gz b/data/AB/1974/04_correctedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4b22e2c3e141a453a88f320d14d4dce26e3db7a8
--- /dev/null
+++ b/data/AB/1974/04_correctedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ed18e34920d0f4a6402cf9a96ecdd12dc47ccb3a2abab0976bc5911dff8ec0
+size 22540482
diff --git a/data/AB/1977/02_extractedxml.tar.gz b/data/AB/1977/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d3d86d0b41745fb8b6e22af9b580ab3835c07dea
--- /dev/null
+++ b/data/AB/1977/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712d29e255e7df6857be63ca07b46fe767193bba618694325da6ab1ad69491e7
+size 314960855
diff --git a/data/AB/1980/02_extractedxml.tar.gz b/data/AB/1980/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..9a49a4f352da8f831afa549a7ab7bfdfb699bba1
--- /dev/null
+++ b/data/AB/1980/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0baf515b60277460abe248e29981e2fb35cb335b5bcd8fe6efcb8d325738f59
+size 325333041
diff --git a/data/AB/1981/02_extractedxml.tar.gz b/data/AB/1981/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..94e8d0fa81abff2c90a60f0974f392c63fcdca3b
--- /dev/null
+++ b/data/AB/1981/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ff09ddaa77c85d59601eed6e8817489db27a055f353cdef9aae7a28e24db03
+size 341425000