Closes #1333: Integrate mining algorithm for RISIS RI

Intoducing RISIS related test case in the community mining integration tests suite.

This squashed commit includes the following set of projects.sql madis script related changes:
* add risis generic mining and services
* risis to lower case

iis-wf/iis-wf-referenceextraction/src/main/resources/eu/dnetlib/iis/wf/referenceextraction/community/main_sqlite/oozie_app/lib/scripts/communitiesextract.sql

@@ -82,4 +82,37 @@ select docid, conceptId, conceptLabel, stripchars(middle,'.)(,[]') as middle, pr
 from (
 setschema 'docid,prev,middle,next' select c1, textwindow2s(keywords(filterstopwords(c2)),7,1,3, '\bDARIAH') from pubs where c2 is not null
 ), grants where conceptLabel="DARIAH EU" and (not regexprmatches("edariah",lower(middle)) and not regexprmatches("riyadh",lower(context)) )
-) group by docid;
+) group by docid
+
+union all
+
+-- RISIS
+select jdict('documentId', id, 'conceptId', 'risis', 'confidenceLevel', 0.8, 'textsnippet', prev||" <<< "||middle||" >>> "||next) from
+(
+select * from
+(
+-- cortext
+select id, "CORTEXT" as ma, prev, middle, next from (setschema 'id,text,prev,middle,next' select id, text, textwindow2s(lower(text), 10,1,10, "(?:\b|\W)cortext(?:\b|\d)") from (setschema 'id,text' select c1,c2 from pubs)) where 
+regexprmatches("cortext\.net|cortext\.org|www\.cortext\.|risis|ifris|text analysis|text mining|software|platform|plateforme|cortext manager|analysis|mining|nltk|github\.com\/cortext\/|corpus|\blisis\b|\b\inrae\b", prev||" "||middle||" "||next)
+or regexprmatches("\bRISIS\b|\bINRAE\b|CorTexT|\bLISIS\b",text)
+
+-- gate
+union all
+
+select id, "GATE" as ma, prev, middle, next   from (setschema 'id,prev,middle,next' select id, textwindow2s(text, 10,1,10, "\bGATE(?:\b|\d)|gatecloud|gate\.ac\.uk") from (setschema 'id,text' select c1,c2 from pubs)) 
+where regexprmatches("text mining|gatecloud|gate\.ac\.uk|\buima\b|classifier|semantic|\bnlp\b|text engineering|natural language|language engineering|information extraction|text analytics|cunningham|text process|architecture text|maynard|tablan|bontcheva|gate framework|tokenizer|tokeniser|sheffield|text annotation|language processing|\bnltk\b|treetagger|\byatea\b", lower(prev||" "||middle||" "||next))
+
+
+union all
+
+select id, upper(regexpr("(orgreg|firmreg)",middle)) as ma, prev, middle, next from (setschema 'id,text,prev,middle,next' select id, text, textwindow2s(lower(text), 10,1,10, "\borgreg\b|\bfirmreg\b") from (setschema 'id,text' select c1,c2 from pubs)) 
+where regexprmatches("\brisis\b", prev||" "||middle||" "||next) or regexprmatches("\bRISIS\b", text)
+
+
+
+union all
+
+select id, "risis" as ma, prev, middle, next from (setschema 'id,prev,middle,next' select id, textwindow2s(text, 10,1,10, "\bRISIS\b|\bRISIS1\b|\bRISIS2\b|\brisis\.eu\b") from (setschema 'id,text' select c1,c2 from pubs)) 
+where (regexprmatches("recherche|patent|grant|support|acknowledge|innovation|research", prev||" "||middle||" "||next) and not regexprmatches("risis\.eu",lower(middle)) )
+      or regexprmatches("risis\.eu",lower(middle))
+) group by id) ;

iis-wf/iis-wf-referenceextraction/src/test/resources/eu/dnetlib/iis/wf/referenceextraction/community/data/concept.json

@@ -54,3 +54,11 @@
       {"name": "suggestedAcknowledgement", "value":""}
    ]
 }
+{
+   "id": "risis", 
+   "label": "RISIS", 
+   "params": []
+}
+
+
+

iis-wf/iis-wf-referenceextraction/src/test/resources/eu/dnetlib/iis/wf/referenceextraction/community/data/document_text.json

@@ -4,5 +4,5 @@
 {"text":"Acknowledgments Marc Ruff team was supported by grant from Instruct, part of the European Strategy Forum on Research Infrastructure (ESFRI) supported by national members subscription. ","id":"50|dedup_wf_001::ed8e5e23ebff00fd270be8e10259c252"}
 {"text":"Liaison with the DARIAH research infrastructure was institutionalized at the start of the project by the arrangement for the University of Oxford to act as the official liaison partner","id":"50|belief______::b1d27bbd867754230abfb55238e1e627"}
 {"text":"Acknowledgements This work was supported by ANR programs Investissements d'Avenir: MetaboHub, EMBRC-France, France Génomique, Institut Français de Bioinformatique.","id":"50|dedup_wf_001::f6e0a74009879de5c13103f1e4b99827"}
-
-{"text":"We acknowledge support of this work by the project “INSPIRED” (MIS 5002550), which is implemented under the Action Reinforcement of the Research and Innovation Infrastructure","id":"50|pmid________::1d7ef02818bae06e15ab18bc6a986ca7"}
+{"text":"We acknowledge support of this work by the project “INSPIRED” (MIS 5002550), which is implemented under the Action Reinforcement of the Research and Innovation Infrastructure","id":"50|pmid________::1d7ef02818bae06e15ab18bc6a986ca7"}
+{"text":"Acknowledgements This work was supported by RISIS2 (Research Infrastructure for and Innovation Policy Studies)","id":"50|doi_________::38502b081c386672f71750c99160e836"}

iis-wf/iis-wf-referenceextraction/src/test/resources/eu/dnetlib/iis/wf/referenceextraction/community/data/document_to_community.json

@@ -40,4 +40,9 @@
   "confidenceLevel": 0.5,
   "textsnippet": "acknowledge support work project INSPIRED MIS 5002550 implemented Action Reinforcement"
 }
-
+{
+  "documentId": "50|doi_________::38502b081c386672f71750c99160e836",
+  "conceptId": "risis",
+  "confidenceLevel": 0.8,
+  "textsnippet": "Acknowledgements This work was supported by <<< RISIS2 >>> (Research Infrastructure for and Innovation Policy Studies)"
+}

iis-wf/iis-wf-referenceextraction/src/test/resources/eu/dnetlib/iis/wf/referenceextraction/community/data/report.json

@@ -4,4 +4,5 @@
 {"key":"processing.referenceExtraction.community.references.byrootid.embrc", "type":"COUNTER", "value": "1"}
 {"key":"processing.referenceExtraction.community.references.byrootid.eric", "type":"COUNTER", "value": "1"}
 {"key":"processing.referenceExtraction.community.references.byrootid.fli", "type":"COUNTER", "value": "1"}
-{"key":"processing.referenceExtraction.community.references.byrootid.inspired-ris", "type":"COUNTER", "value": "1"}
+{"key":"processing.referenceExtraction.community.references.byrootid.inspired-ris", "type":"COUNTER", "value": "1"}
+{"key":"processing.referenceExtraction.community.references.byrootid.risis", "type":"COUNTER", "value": "1"}