Make mapping for 856 less strict #2070

Due to missing indicator 1 = 4 some links were not created. Since 856 with an empty indicator which says missing information could also link to an http-page I change the 8564? -> 856??

src/main/resources/alma/fix/identifiers.fix

@@ -19,7 +19,7 @@ end
 # 1. Indicator: 4 = HTTP
 set_array("@urnLinks")
 
-do list(path:"8564?", "var":"$i")
+do list(path:"856??", "var":"$i")
   if all_match("$i.u", "^http.*(urn=|\\.(org|de)/)urn:.+$") # This should ignore repository links like: https://sammlungen.ulb.uni-muenster.de/urn/urn:nbn:de:hbz:6-85659520092
     copy_field("$i.u", "urn[].$append")
     copy_field("$i.u", "@urnLinks.$append")
@@ -100,12 +100,12 @@ end
 # Sometimes dois are not set in 024 then we could pick up the missing from 856.
 # 856 - Electronic Location and Access (R) - Subfield: $u (R) $3 (NR)
 # 1. Indicator: 4 = HTTP
-do list(path:"8564?", "var":"$i")
+do list(path:"856??", "var":"$i")
   if all_match("$i.u", ".*doi.org.*(10\\.(\\d)+/(\\S)+).*") # Volltext
     copy_field("$i.u", "doi[].$append")
-    replace_all("doi[].$last", ".*doi.org.*(10\\.(\\d)+/(\\S)+).*", "$1")
   end
 end
+replace_all("doi[].*", ".*doi.org.*(10\\.(\\d)+/(\\S)+).*", "$1")
 uniq("doi[]")
 
 # 035 - System Control Number (R) - Subfield: $a (NR)

src/main/resources/alma/fix/relatedRessourcesAndLinks.fix

@@ -35,7 +35,7 @@ do list(path: "rpbId", "var": "$i")
 end
 
 # DBIS
-do list(path: "8564?", "var":"$i")
+do list(path: "856??", "var":"$i")
   if exists("$i.u")
     if all_match("$i.x", ".*DBIS.*")
       copy_field("$i.u", "sameAs[].$append.id")
@@ -254,7 +254,7 @@ replace_all("secondaryForm[].*.id", "^\\(DE-600\\)(.*)$", "http://lobid.org/reso
 
 set_array("tableOfContents[]")
 
-do list(path: "8564?", "var":"$i")
+do list(path: "856??", "var":"$i")
   if all_match("$i.3", "^[Ii][Nn][Hh][aA][lL][tT][sS][vV].*") # Inhaltsverzeichnis
     copy_field("$i.3", "tableOfContents[].$append.label")
     copy_field("$i.u", "tableOfContents[].$last.id")
@@ -263,7 +263,7 @@ end
 
 set_array("description[]")
 
-do list(path: "8564?", "var":"$i")
+do list(path: "856??", "var":"$i")
   if all_match("$i.3", "^[Ii][Nn][Hh][aA][lL][tT][sS][tT].*") # Inhaltstext
     copy_field("$i.3", "description[].$append.label")
     copy_field("$i.u", "description[].$last.id")
@@ -272,7 +272,7 @@ end
 
 set_array("seeAlso[]")
 
-do list(path: "8564?", "var":"$i")
+do list(path: "856??", "var":"$i")
   if all_match("$i.3", "^[zZ][uU][sS].*") # Zusätzliche Angaben
     copy_field("$i.3", "seeAlso[].$append.label")
     copy_field("$i.u", "seeAlso[].$last.id")
@@ -281,7 +281,7 @@ end
 
 set_array("fulltextOnline[]")
 
-do list(path: "8564?", "var":"$i")
+do list(path: "856??", "var":"$i")
   if exists("$i.u")
     unless any_match("$i.u",".*(doi.org|urn=urn:|\\.(org|de)/urn:).*") # This should not skip repository links like: https://sammlungen.ulb.uni-muenster.de/urn/urn:nbn:de:hbz:6-85659520092
       if all_equal("$i.z", "kostenfrei") # kostenfrei, added Digitalisierung not only Verlag or Agentur as filter
@@ -439,7 +439,7 @@ end
 
 # 856 - Electronic Location and Access (R) - Subfield: $x - Nonpublic note (R)
 # TODO: Check if src/test/resources/alma-fix/(CKB)5280000000199164.xml is also an EZB titel even when it has no 865.
-do list(path:"8564?", "var":"$i")
+do list(path:"856??", "var":"$i")
   if any_equal("$i.x","EZB") # can test x and x.*
     add_field("inCollection[].$append.id", "http://lobid.org/resources/HT016356466#!")
     add_field("inCollection[].$last.label", "Elektronische Zeitschriftenbibliothek (EZB)")
@@ -452,7 +452,7 @@ end
 
 # edoweb
 
-do list(path:"8564?", "var":"$i")
+do list(path:"856??", "var":"$i")
   if any_match("$i.u","^.*edoweb.*") # can test x and x.*
     add_field("inCollection[].$append.id", "http://lobid.org/resources/HT016925914#!")
     add_field("inCollection[].$last.label", "Edoweb Rheinland-Pfalz")
@@ -463,7 +463,7 @@ end
 
 
 # TODO: AlephMorph checked for ellinet in "078r1.a" but publisso is also stated in the Link URI is that enough?
-do list(path:"8564?", "var":"$i")
+do list(path:"856??", "var":"$i")
   if any_match("$i.u","^.*publisso.*") # can test x and x.*
     add_field("inCollection[].$append.id", "http://repository.publisso.de")
     add_field("inCollection[].$last.label", "Fachrepositorium Lebenswissenschaften")

src/test/resources/alma-fix/990177418660206441.json

@@ -80,6 +80,22 @@
     "id" : "http://worldcat.org/oclc/838434577",
     "label" : "OCLC Ressource"
   } ],
+  "fulltextOnline" : [ {
+    "label" : "Volltext",
+    "id" : "http://www.gbv.de/dms/belser/aszese/74817-1.pdf"
+  }, {
+    "label" : "Volltext",
+    "id" : "http://www.gbv.de/dms/belser/aszese/74817-2.pdf"
+  }, {
+    "label" : "Volltext",
+    "id" : "http://www.gbv.de/dms/belser/aszese/74817-3.pdf"
+  }, {
+    "label" : "Volltext",
+    "id" : "http://www.gbv.de/dms/belser/aszese/74817-4.pdf"
+  }, {
+    "label" : "Volltext",
+    "id" : "http://www.gbv.de/dms/belser/aszese/74817-5.pdf"
+  } ],
   "inCollection" : [ {
     "id" : "https://nrw.digibib.net/search/hbzvk/",
     "label" : "DigiBib hbz Verbundkatalog",

src/test/resources/alma-fix/990184766040206441.json

@@ -13,6 +13,7 @@
   "almaMmsId" : "990184766040206441",
   "hbzId" : "HT016770284",
   "deprecatedUri" : "http://lobid.org/resources/HT016770284#!",
+  "doi" : [ "10.48644/mpirg_sisis_125001" ],
   "oclcNumber" : [ "179716832" ],
   "publication" : [ {
     "startDate" : "1883",
@@ -73,12 +74,19 @@
   }, {
     "id" : "http://worldcat.org/oclc/179716832",
     "label" : "OCLC Ressource"
+  }, {
+    "id" : "https://doi.org/10.48644/mpirg_sisis_125001",
+    "label" : "mpirg_sisis_125001"
   } ],
   "primaryForm" : [ {
     "id" : "http://lobid.org/resources/HT000522767#!",
     "label" : "Elektronische Reproduktion von HT000522767",
     "note" : [ "Elektronische Reproduktion von" ]
   } ],
+  "fulltextOnline" : [ {
+    "id" : "https://doi.org/10.48644/mpirg_sisis_125001",
+    "label" : "DOI-Link"
+  } ],
   "inCollection" : [ {
     "id" : "https://nrw.digibib.net/search/hbzvk/",
     "label" : "DigiBib hbz Verbundkatalog",