Adding extraction primitives

modules/microsite/docs/dev/adr/process-files.puml

@@ -0,0 +1,43 @@
+@startuml
+scale 1200 width
+title: Processing Files
+skinparam monochrome true
+skinparam backgroundColor white
+skinparam rectangle {
+    roundCorner<<Input>> 25
+    roundCorner<<Output>> 5
+}
+rectangle Input <<Input>> {
+  file "html"
+  file "plaintext"
+  file "image"
+  file "msoffice"
+  file "rtf"
+  file "odf"
+  file "pdf"
+}
+
+node toBoth [
+  PDF + TXT
+]
+node toPdf [
+  PDF
+]
+node toTxt [
+  TXT
+]
+
+image --> toBoth:<tesseract>
+html --> toPdf:<wkhtmltopdf>
+toPdf --> toTxt:[pdfbox]
+plaintext --> html:[flexmark]
+msoffice --> toPdf:<unoconv>
+msoffice --> toTxt:[poi]
+rtf --> toTxt:[jdk]
+rtf --> toPdf:<unoconv>
+odf --> toTxt:[tika]
+odf --> toPdf:<unoconv>
+pdf --> toTxt:<tesseract>
+pdf --> toTxt:[pdfbox]
+plaintext -> toTxt:[identity]
+@enduml