Use collective data with NER annotation

modules/joex/src/main/resources/reference.conf

@@ -248,6 +248,29 @@ docspell.joex {
     # should suffice. Default is 10000, which are about 2-3 pages
     # (just a rough guess, of course).
     max-length = 10000
+
+    # A working directory for the analyser to store temporary/working
+    # files.
+    working-dir = ${java.io.tmpdir}"/docspell-analysis"
+
+    regex-ner {
+      # Whether to enable custom NER annotation. This uses the address
+      # book of a collective as input for NER tagging (to automatically
+      # find correspondent and concerned entities). If the address book
+      # is large, this can be quite memory intensive and also makes text
+      # analysis slower. But it greatly improves accuracy. If this is
+      # false, NER tagging uses only statistical models (that also work
+      # quite well).
+      #
+      # This setting might be moved to the collective settings in the
+      # future.
+      enabled = true
+
+      # The NER annotation uses a file of patterns that is derived from
+      # a collective's address book. This is is the time how long this
+      # file will be kept until a check for a state change is done.
+      file-cache-time = "1 minute"
+    }
   }
 
   # Configuration for converting files into PDFs.