|
1
|
<RESOURCE_PROFILE>
|
|
2
|
<HEADER>
|
|
3
|
<RESOURCE_IDENTIFIER value="05192beb-dccb-4d6b-b7af-57193b9e7538_VHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZXMvVHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZVR5cGU="/>
|
|
4
|
<RESOURCE_TYPE value="TransformationRuleDSResourceType"/>
|
|
5
|
<RESOURCE_KIND value="TransformationRuleDSResources"/>
|
|
6
|
<RESOURCE_URI value=""/>
|
|
7
|
<DATE_OF_CREATION value="2017-03-20T17:08:37+00:00"/>
|
|
8
|
</HEADER>
|
|
9
|
<BODY>
|
|
10
|
<CONFIGURATION>
|
|
11
|
<IMPORTED/>
|
|
12
|
<SCRIPT>
|
|
13
|
<TITLE>dc_cleaning_OPENAIREplus_compliant_SCIndeksORCID</TITLE>
|
|
14
|
<CODE>declare_script "dc_cleaning_OpenAIREplus_compliant_SCIndeksORCID";
|
|
15
|
declare_ns oaf = "http://namespace.openaire.eu/oaf";
|
|
16
|
declare_ns dri = "http://www.driver-repository.eu/namespace/dri";
|
|
17
|
declare_ns dr = "http://www.driver-repository.eu/namespace/dr";
|
|
18
|
declare_ns dc = "http://purl.org/dc/elements/1.1/";
|
|
19
|
declare_ns prov = "http://www.openarchives.org/OAI/2.0/provenance";
|
|
20
|
declare_ns oai = "http://www.openarchives.org/OAI/2.0/";
|
|
21
|
declare_ns xs = "http://www.w3.org/2001/XMLSchema";
|
|
22
|
$var0 = "''";
|
|
23
|
$varFP7 = "'corda_______::'";
|
|
24
|
$varH2020 = "'corda__h2020::'";
|
|
25
|
$varFCT="'fct_________::'";
|
|
26
|
$varWT = "'wt__________::'";
|
|
27
|
$varMESTD = "'mestd_______::'";
|
|
28
|
$varDummy = "''";
|
|
29
|
static $varDatasourceid = getValue(PROFILEFIELD, [xpath:"concat('collection(&apos;/db/DRIVER/RepositoryServiceResources&apos;)//RESOURCE_PROFILE[.//EXTRA_FIELDS/FIELD[key=&quot;NamespacePrefix&quot;][value=&quot;', //oaf:datasourceprefix, '&quot;]]')", xpath:"//EXTRA_FIELDS/FIELD[key='OpenAireDataSourceId']/value"]);
|
|
30
|
static $varRepoid = xpath:"//dri:repositoryId";
|
|
31
|
static $varOfficialname = getValue(PROFILEFIELD, [xpath:"concat('collection(&apos;/db/DRIVER/RepositoryServiceResources&apos;)//RESOURCE_PROFILE[.//EXTRA_FIELDS/FIELD[key=&quot;NamespacePrefix&quot;][value=&quot;', //oaf:datasourceprefix, '&quot;]]')", xpath:"//CONFIGURATION/OFFICIAL_NAME"]);
|
|
32
|
dri:objIdentifier = xpath:"//dri:objIdentifier";
|
|
33
|
dri:repositoryId = $varRepoid;
|
|
34
|
dri:recordIdentifier = xpath:"//dri:recordIdentifier";
|
|
35
|
if xpath:"//oai:setSpec[.='col_data_1694'] or //dc:creator[starts-with(., 'test')]" dc:coverage = skipRecord(); else $varDummy = "''";
|
|
36
|
|
|
37
|
//apply xpath:"//dc:creator" if xpath:"string-length(.) > 0 and not(contains(., 'US National Cancer Institute'))" dc:creator = xpath:"normalize-space(.)"; else $varDummy = "''";
|
|
38
|
$varOrcidName = xpath:"//dc:creator[string-length(.) > 0]/replace(.,'^(.*?)(; id_orcid .*?)$','$1')";
|
|
39
|
$varOrcidOrcid = xpath:"//dc:creator[string-length(.) > 0]/substring-after(.,'id_orcid ')";
|
|
40
|
dc:creator = set(xpath:"$varOrcidName", @nameIdentifier = xpath:"subsequence($varOrcidOrcid,position(),1)";, @nameIdentifierScheme=xpath:"replace(subsequence($varOrcidOrcid,position(),1),'^.+$','ORCID')";, @schemeUri=xpath:"replace(subsequence($varOrcidOrcid,position(),1),'^.+$','http://orcid.org/')";);
|
|
41
|
|
|
42
|
if xpath:"//dc:title[string-length(.)> 0] and not(//dc:creator[.='Test'])" $varDummy = "''"; else dc:coverage = skipRecord();
|
|
43
|
apply xpath:"//dc:title" if xpath:"string-length(.) > 0" dc:title = xpath:"normalize-space(.)"; else $varDummy = "''";
|
|
44
|
//
|
|
45
|
//apply xpath:"//dc:subject" if xpath:"string-length(.) > 0" dc:subject = xpath:"normalize-space(.)"; else $varDummy = "''";
|
|
46
|
//
|
|
47
|
// subject
|
|
48
|
// gather subjects: from fields setSpec, subject, classification, keywords
|
|
49
|
// assign context: if field value or @xsi:type refers to an approved vocabulary/classification/thesaurus, assign its normed code
|
|
50
|
// normalise form: in case of approved vocabulary/classification/thesaurus: 'context:subject', otherwise: 'subject [additional information]'
|
|
51
|
// remove duplicates: identical pairs of value/term and context/vocabulary
|
|
52
|
$subjVocHarv = xpath:"'bicssc','bk','ddc','gok','jel classification','jel codes','jelelement','jel','lcsh','mesh','msc','rvk'"; // subject contexts/vocabularies as harvested
|
|
53
|
$subjVocCode = xpath:"'bicssc','bk','ddc','gok','jel', 'jel', 'jel', 'jel','lcsh','mesh','msc','rvk'"; // subject contexts/vocabularies as normed within OpenAIRE
|
|
54
|
$subjVoc = xpath:"concat('(',string-join($subjVocHarv,'|'),')')"; // regular expression for subject contexts
|
|
55
|
$subjVocVal = xpath:"concat('^\s*','((info:eu-repo/classification/)?',$subjVoc,'[:/].*)')"; // regular expression for subject contexts in field values
|
|
56
|
$subjVocPar = xpath:"concat('^\s*','(dcterms:\s*)?',$subjVoc,'\s*$')"; // regular expression for subject contexts in field parameters
|
|
57
|
// subject context: approved vocabulary/classification/thesaurus in field value
|
|
58
|
//dc:subject = set(xpath:"(//dc:subject|//*[local-name()='setSpec'])[string-length(.) > 0 and matches(., $subjVocVal,'i')]", @classid=xpath:"subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(.),$subjVocVal,'$3','i')),1)";, @classname=xpath:"subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(.),$subjVocVal,'$3','i')),1)";, @schemeid=xpath:"'dnet:subject_classification_typologies'";, @schemename=xpath:"'dnet:subject_classification_typologies'";);
|
|
59
|
$subjListInVal = xpath:"(//dc:subject|//*[local-name()='setSpec'])[string-length(.) > 0 and matches(., $subjVocVal,'i')]/concat(./subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(.),$subjVocVal,'$3','i')),1),':',normalize-space(replace(.,'(info:eu-repo/classification/)?([^/:]*)[:/](.*)','$3')))";
|
|
60
|
// subject context: approved vocabulary/classification/thesaurus in field parameter
|
|
61
|
//dc:subject = set(xpath:"(//dc:subject|//*[local-name()='classification'])[string-length(.) > 0 and matches(./@xsi:type, $subjVocPar,'i')]", @classid=xpath:"subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(./@xsi:type),$subjVocPar,'$2','i')),1)";, @classname=xpath:"subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(./@xsi:type),$subjVocPar,'$2','i')),1)";, @schemeid=xpath:"'dnet:subject_classification_typologies'";, @schemename=xpath:"'dnet:subject_classification_typologies'";);
|
|
62
|
$subjListInPar = xpath:"(//dc:subject|//*[local-name()='classification'])[string-length(.) > 0 and matches(./@xsi:type, $subjVocPar,'i')]/concat(./subsequence($subjVocCode,index-of($subjVocHarv,replace(lower-case(./@xsi:type),$subjVocPar,'$2','i')),1),':',normalize-space(.))";
|
|
63
|
// subject context: approved vocabulary/classification/thesaurus in field value or parameter
|
|
64
|
$subjListInParAndVal = xpath:"distinct-values(insert-before($subjListInVal,0,$subjListInPar))";
|
|
65
|
dc:subject = set(xpath:"$subjListInParAndVal", @classid=xpath:"substring-before(.,':')";, @classname=xpath:"substring-before(.,':')";, @schemeid=xpath:"'dnet:subject_classification_typologies'";, @schemename=xpath:"'dnet:subject_classification_typologies'";);
|
|
66
|
// subject context: no (approved) vocabulary/classification/thesaurus
|
|
67
|
//dc:subject = set(xpath:"(//dc:subject|//*[local-name()='classification']|//*[local-name()='keywords'])[string-length(.) > 0 and not(matches(., $subjVocVal,'i')) and not(matches(./@xsi:type,$subjVocPar,'i'))]", @classid=xpath:"'keyword'";, @classname=xpath:"'keyword'";, @schemeid=xpath:"'dnet:result_subject'";, @schemename=xpath:"'dnet:result_subject'";);
|
|
68
|
//$subListKeywords = xpath:"distinct-values((//dc:subject|//*[local-name()='classification']|//*[local-name()='keywords'])[string-length(.) > 0 and not(matches(., $subjVocVal,'i')) and not(matches(./@xsi:type,$subjVocPar,'i'))]/replace(concat(normalize-space(replace(.,'((info:eu-repo/classification/[^/]*/)|([^:]*:))(.*)','$4')),' [',normalize-space(concat(replace(./@xsi:type,'dcterms:',''),' ',substring-before(replace(.,'(info:eu-repo/classification/)?([^/:]*)[/:](.*)','$2:$3'),':'))),']'),' \[\]',''))";
|
|
69
|
$subjListKeywordsInfo = xpath:"(//dc:subject|//*[local-name()='classification']|//*[local-name()='keywords'])[string-length(.) > 0 and not(matches(., $subjVocVal,'i')) and not(matches(./@xsi:type,$subjVocPar,'i')) and starts-with(.,'info:eu-repo/classification/')]
|
|
70
|
/replace(concat(normalize-space(replace(.,'info:eu-repo/classification/[^/]*/(.*)','$1')),' [',normalize-space(concat(replace(./@xsi:type,'dcterms:',''),' ',replace(.,'info:eu-repo/classification/([^/]*)/.*','$1'))),']'),' \[\]','')";
|
|
71
|
$subjListKeywordsColon = xpath:"(//dc:subject|//*[local-name()='classification']|//*[local-name()='keywords'])[string-length(.) > 0 and not(matches(., $subjVocVal,'i')) and not(matches(./@xsi:type,$subjVocPar,'i')) and not(starts-with(.,'info:eu-repo/classification/'))]/replace(concat(normalize-space(replace(.,'[^:]*:(.*)','$1')),' [',normalize-space(concat(replace(./@xsi:type,'dcterms:',''),' ',substring-before(.,':'))),']'),' \[\]','')";
|
|
72
|
$subjListKeywordsInfoAndColon = xpath:"distinct-values(insert-before($subjListKeywordsInfo,0,$subjListKeywordsColon))";
|
|
73
|
dc:subject = set(xpath:"$subjListKeywordsInfoAndColon", @classid=xpath:"'keyword'";, @classname=xpath:"'keyword'";, @schemeid=xpath:"'dnet:result_subject'";, @schemename=xpath:"'dnet:result_subject'";);
|
|
74
|
//
|
|
75
|
apply xpath:"//dc:publisher" if xpath:"string-length(.) > 0" dc:publisher = xpath:"normalize-space(.)"; else $varDummy = "''";
|
|
76
|
apply xpath:"//dc:source" if xpath:"string-length(.) > 0" dc:source = xpath:"normalize-space(.)"; else $varDummy = "''";
|
|
77
|
dc:contributor = xpath:"//dc:contributor";
|
|
78
|
dc:description = xpath:"string-join(//dc:description[concat(normalize-space(.), '')], codepoints-to-string(10))";
|
|
79
|
$varHttpTest = "''";
|
|
80
|
if xpath:"//dc:identifier[starts-with(., 'http')][not(starts-with(., 'http://hdl.handle.net/123456789') or starts-with(., 'https://hdl.handle.net/123456789'))]" $varHttpTest = "true"; else dc:identifier = skipRecord();
|
|
81
|
apply xpath:"//dc:identifier" if xpath:"starts-with(normalize-space(.), 'http')" dc:identifier = xpath:"normalize-space(.)"; else dr:CobjIdentifier = xpath:"normalize-space(.)";
|
|
82
|
dr:dateOfCollection = xpath:"//dri:dateOfCollection";
|
|
83
|
static dr:dateOfTransformation = xpath:"current-dateTime()";
|
|
84
|
dc:type = xpath:"//dc:type";
|
|
85
|
dc:format = xpath:"//dc:format";
|
|
86
|
dc:date = xpath:"//dc:date";
|
|
87
|
dc:language = Convert(xpath:"//dc:language", Languages);
|
|
88
|
//dc:language = "eng";
|
|
89
|
//if xpath:"//dc:rights[text()='info:eu-repo/semantics/openAccess']" dc:publisher = xpath:"//dc:publisher"; else dc:publisher = skipRecord();
|
|
90
|
$varDateAccepted = Convert(xpath:"descendant-or-self::dc:date", DateISO8601, "yyyy-MM-dd", "min()");
|
|
91
|
if xpath:"//oaf:datasourceprefix[.='od_______883']" oaf:dateAccepted = Convert(xpath:"descendant-or-self::dc:date[3]", DateISO8601); else $varDummy= "''";
|
|
92
|
if xpath:"//oaf:datasourceprefix[.='od______3063']" oaf:dateAccepted = Convert(xpath:"descendant-or-self::dc:date", DateISO8601); else $varDummy= "''";
|
|
93
|
if xpath:"(//oaf:datasourceprefix[.='od______2658'] or //oaf:datasourceprefix[.='od______1318']) and starts-with($varDateAccepted, '1000')" oaf:dateAccepted = $varDummy; else $varDummy= "''";
|
|
94
|
if xpath:"not(//oaf:datasourceprefix[.='od_______883']) and not(//oaf:datasourceprefix[.='od______3063']) and not(starts-with($varDateAccepted, '10') or starts-with($varDateAccepted, '00'))" oaf:dateAccepted = $varDateAccepted; else $varDummy= "''";
|
|
95
|
// apply xpath:"//dc:date" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/date')" oaf:embargoenddate = RegExpr(xpath:"normalize-space(.)", $var0, "s/^(.*info:eu-repo\/date\/embargoEnd\/)//gmi"); else $var0 = "''";
|
|
96
|
$varEmbargoEnd = xpath:"//dc:date[matches(normalize-space(.), '(.*)(info:eu-repo/date/embargoEnd/)(\d\d\d\d-\d\d-\d\d)', 'i')][contains(lower-case(.), 'info:eu-repo')]/replace(normalize-space(.), '(.*)(info:eu-repo/date/embargoEnd/)(\d\d\d\d-\d\d-\d\d)', '$3', 'i')";
|
|
97
|
oaf:embargoenddate = $varEmbargoEnd;
|
|
98
|
// FP7
|
|
99
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')][year-from-date(xs:date(max(($varDateAccepted, '0001-01-01')))) gt 2006][contains(lower-case(.), 'info:eu-repo')]/concat($varFP7, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/fp7/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))";
|
|
100
|
// ERC (provided by OAPEN)
|
|
101
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement/european research council.*/-/)(\d\d\d\d\d\d)(.*)', 'i')][contains(lower-case(.), 'info:eu-repo')]/concat($varFP7, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement/european research council.*/-/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))";
|
|
102
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement/european union.* seventh framework programme.*/-/)(\d\d\d\d\d\d)(.*)', 'i')][contains(lower-case(.), 'info:eu-repo')]/concat($varFP7, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement/european union.* seventh framework programme.*/-/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))";
|
|
103
|
// H2020
|
|
104
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')][year-from-date(xs:date(max(($varDateAccepted, '0001-01-01')))) gt 2013][contains(lower-case(.), 'info:eu-repo')]/concat($varH2020, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/h2020/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))";
|
|
105
|
// FCT
|
|
106
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(info:eu-repo/grantagreement/fct)/(.+)/(\d+)(.*)', 'i')][contains(lower-case(.), 'info:eu-repo')]/concat($varFCT, replace(normalize-space(.), '(info:eu-repo/grantagreement/fct)/(.+)/(\d+)(.*)', '$3', 'i')))";
|
|
107
|
// MESTD
|
|
108
|
oaf:projectid = xpath:"//dc:relation[matches(normalize-space(.), '(info:eu-repo/grantagreement/mestd)/(.+)/(\d+)(.*)', 'i')][contains(lower-case(.), 'info:eu-repo')]/concat($varMESTD, replace(normalize-space(.), '(info:eu-repo/grantagreement/mestd)/(.+)/(\d+)(.*)', '$3', 'i'))";
|
|
109
|
// WT
|
|
110
|
oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement/wellcome trust/-/)(\d\d\d\d\d\d)(.*)', 'i')][contains(lower-case(.), 'info:eu-repo')]/concat($varWT, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement/wellcome trust/-/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))";
|
|
111
|
dc:relation = xpath:"//dc:relation";
|
|
112
|
//comment-js-09-10-2012 apply xpath:"//dc:rights" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/semantics')" dc:rights = empty; else dc:rights = xpath:"normalize-space(.)";
|
|
113
|
//
|
|
114
|
//
|
|
115
|
oaf:collectedDatasourceid = xpath:"$varDatasourceid";
|
|
116
|
//
|
|
117
|
// dr:CobjCategory = Convert(xpath:"//dc:type", TextTypologies);
|
|
118
|
// if xpath:"//dc:type[1]/lower-case(.) = 'text'" dr:CobjCategory = Convert(xpath:"reverse(//dc:type)", TextTypologies); else dr:CobjCategory = Convert(xpath:"//dc:type", TextTypologies);
|
|
119
|
if xpath:"//dc:type[1]/lower-case(.) = 'text'" dr:CobjCategory = Convert(xpath:"reverse(//dc:type) | //oai:setSpec", TextTypologies); else dr:CobjCategory = Convert(xpath:"//dc:type | //oai:setSpec", TextTypologies);
|
|
120
|
//
|
|
121
|
if xpath:"(xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) gt current-date())" oaf:accessrights = "EMBARGO"; else $var0 = "''";
|
|
122
|
if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics') and not(starts-with(normalize-space(.), 'info:eu-repo/semantics/embargo')) and not((xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) gt current-date()))]" oaf:accessrights = Convert(xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics')]", AccessRights); else $var0 = "''";
|
|
123
|
if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics/embargo') and not((xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) gt current-date()))]" oaf:accessrights = "OPEN"; else $var0 = "''";
|
|
124
|
if xpath:"count(//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics/')]) eq 0" oaf:accessrights = "OPEN"; else $var0 = "''";
|
|
125
|
//
|
|
126
|
// apply xpath:"//dc:rights" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/semantics') and (xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) gt current-date())" oaf:accessrights = Convert(xpath:"normalize-space(.)", AccessRights); else dc:rights = xpath:".";
|
|
127
|
// apply xpath:"//dc:rights" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/semantics') " oaf:accessrights = Convert(xpath:"normalize-space(.)", AccessRights); else dc:rights = xpath:".";
|
|
128
|
// if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics/restrictedAccess') ]" oaf:accessrights = "RESTRICTED"; else $var0 = "''";
|
|
129
|
// if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics') and not(xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) lt current-date())]" $var0 = "''"; else oaf:accessrights = "OPEN";
|
|
130
|
// oaf:accessrights = xpath:"//dc:rights[ not(starts-with(normalize-space(.), 'info:eu-repo/semantics')) and xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) lt current-date()]/concat('OPEN')";
|
|
131
|
// oaf:accessrights = xpath:"//dc:rights[not(contains(normalize-space(.), 'info:eu-repo/semantics'))]/normalize-space('OPEN')";
|
|
132
|
// oaf:accessrights = xpath:"not(xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) lt current-date())";
|
|
133
|
//
|
|
134
|
static oaf:collectedFrom = set("''", @name = $varOfficialname; , @id = $varDatasourceid;);
|
|
135
|
static oaf:hostedBy = set("''", @name = $varOfficialname; , @id = $varDatasourceid;);
|
|
136
|
//
|
|
137
|
$varId = identifierExtract('["//dc:identifier", "//dc:relation"]' , xpath:"./*[local-name()='record']" , '(10[.][0-9]{4,}[^\s"/<>]*/[^\s"<>]+)');
|
|
138
|
// 1st param: list of xpath expresssions to be applied on the metadata in json syntax; 2nd param: xpath expression for the metadata record; 3rd param reg expr that matches with a negative lookahead for the first group and extracts digits of the second group
|
|
139
|
$varPmId = identifierExtract('["//dc:relation[starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/pmid/\")]"]' , xpath:"./*[local-name()='record']" , '(?!info:eu-repo/semantics/altIdentifier/pmid/)(\d+)');
|
|
140
|
// $varUrn = xpath:"substring-after(//dc:relation[starts-with(normalize-space(.), 'info:eu-repo/semantics/altIdentifier/urn/')], 'info:eu-repo/semantics/altIdentifier/urn/')";
|
|
141
|
$varUrn = identifierExtract('["//dc:relation[starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/urn/\")]"]' , xpath:"./*[local-name()='record']" , '(?!info:eu-repo/semantics/altIdentifier/urn/)(urn:nbn:.*)');
|
|
142
|
oaf:identifier = set(xpath:"$varId//value", @identifierType = "doi";);
|
|
143
|
oaf:identifier = set(xpath:"$varPmId//value", @identifierType = "pmid";);
|
|
144
|
oaf:identifier = set(xpath:"$varUrn//value", @identifierType = "urn";);
|
|
145
|
oaf:datasourceprefix = xpath:"//oaf:datasourceprefix";
|
|
146
|
//$varJournalTitle = xpath:"//dc:subject[1][//oaf:datasourceprefix[.='dovemedicalp']]/normalize-space(.), //dc:source[1][//oaf:datasourceprefix[.='scindeksserb']]/normalize-space(substring-before(., '('))";
|
|
147
|
$varJournalTitle = xpath:"//dc:subject[1][//oaf:datasourceprefix[.='dovemedicalp']]/normalize-space(.), //dc:source[1][//oaf:datasourceprefix[.='scindeksserb']]/normalize-space(substring-before(., '(')), //dc:source[//oaf:datasourceprefix[.='od______2659']][//dc:relation[matches(., '(issn:|info:eu-repo/semantics/altIdentifier/issn/)','i')]]/normalize-space(replace(., '^(.*?)\s(\d|v\.\s\d).*$', '$1'))";
|
|
148
|
//$varISSN = xpath:"//oai:setSpec[starts-with(., 'ISSN')]/substring-after(., 'ISSN'), //dc:source[starts-with(., 'ISSN:')]/normalize-space(substring-after(., 'ISSN:'))";
|
|
149
|
$varISSN = xpath:"//*[local-name()='setSpec'][starts-with(., 'ISSN')]/substring-after(., 'ISSN'), //dc:source[starts-with(., 'ISSN:')]/normalize-space(substring-after(., 'ISSN:')), //dc:relation[starts-with(., 'issn:') or starts-with(., 'info:eu-repo/semantics/altIdentifier/issn/')]/replace(normalize-space(substring-after(., 'issn')),'[/:]([0-9]{4})-?([0-9X]{4})','$1-$2')";
|
|
150
|
oaf:journal = set($varJournalTitle, @issn = xpath:"$varISSN";);
|
|
151
|
if xpath:"//oaf:datasourceprefix[.='dovemedicalp']" oaf:fulltext = xpath:"concat('file:///mnt/downloaded_dumps/dovepress/', substring-after(//*[local-name()='header']/*[local-name()='identifier'], 'oai:dovepress.com/'), '.pdf')"; else $varDummy= "''";
|
|
152
|
end</CODE>
|
|
153
|
</SCRIPT>
|
|
154
|
</CONFIGURATION>
|
|
155
|
<STATUS/>
|
|
156
|
<SECURITY_PARAMETERS/>
|
|
157
|
</BODY>
|
|
158
|
</RESOURCE_PROFILE>
|