Marekhorst 1586 integrate lens.org patents mining

iis-3rdparty-madis/src/main/resources/eu/dnetlib/iis/3rdparty/scripts/madis/functions/row/text.py

@@ -213,6 +213,17 @@ def cqlfields(*args):
 
 cqlfields.registered=True
 
+def string_split_value(s, a):
+    """
+    Returns the substring of `s` starting from the last occurrence of `a` till the end.
+    If `a` is not found in `s`, returns an empty string.
+    """
+    index = s.rfind(a)  # Find the last occurrence of `a`
+    if index == -1:
+        return ""  # `a` not found
+    return s[index+len(a):]  # Return from last occurrence to the end
+string_split_value.registered = True
+
 def comprspaces(*args):
     """
     .. function:: comprspaces(text1, [text2,...]) -> text

iis-common/src/main/java/eu/dnetlib/iis/common/InfoSpaceConstants.java

@@ -25,6 +25,7 @@ public final class InfoSpaceConstants {
     public static final String ROW_PREFIX_DATASOURCE = "10|";
 
     public static final String OPENAIRE_ENTITY_ID_PREFIX = "openaire____";
+    public static final String LENS_ENTITY_ID_PREFIX = "lens.org____";
 
     public static final String SEMANTIC_CLASS_MAIN_TITLE = "main title";
     public static final String SEMANTIC_CLASS_ALTERNATIVE_TITLE = "alternative title";

iis-schemas/src/main/avro/eu/dnetlib/iis/referenceextraction/patent/DocumentToPatent.avdl

@@ -4,9 +4,8 @@ protocol IIS{
     record DocumentToPatent {
 //      document identifier, foreign key: DocumentWithBasicMetadata.id ("document basic metadata" data store)
         string documentId;
-//      identifier of patent referenced in this document,
-//      foreign key: Patent.appln_nr
-        string appln_nr;
+//      identifier of patent (lens identifier) referenced in this document,
+        string lensId;
 //		Find more details on `confidenceLevel` constraints in eu/dnetlib/iis/README.markdown file.
         float confidenceLevel;
 //      text snippet surrounding the matched reference, required mostly for internal debugging and analytics  

iis-schemas/src/main/avro/eu/dnetlib/iis/referenceextraction/patent/PatentReferenceExtractionInput.avdl

@@ -2,6 +2,10 @@
 protocol IIS{
 
     record PatentReferenceExtractionInput {
-        string appln_nr;
+        string c1;
+        string c2;
+        union{null, string} normal = null;
+        union{null, string} c4 = null;
+        union{null, string} c5 = null;
     }
 }