From 35318027108717ede95b934cd68d691dbc4e20a9 Mon Sep 17 00:00:00 2001 From: Andreas Czerniak Date: Tue, 6 Jul 2021 11:30:56 +0200 Subject: [PATCH 1/2] to solve the scala SI-3623 --- dhp-workflows/dhp-graph-mapper/pom.xml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-graph-mapper/pom.xml b/dhp-workflows/dhp-graph-mapper/pom.xml index 135516e3e..19febb9ed 100644 --- a/dhp-workflows/dhp-graph-mapper/pom.xml +++ b/dhp-workflows/dhp-graph-mapper/pom.xml @@ -35,7 +35,7 @@ -Xmax-classfile-name - 140 + 200 ${scala.version} From ebf3f47a02a0cfe8cb302a2816c054e01d7884c3 Mon Sep 17 00:00:00 2001 From: Andreas Czerniak Date: Wed, 7 Jul 2021 09:29:49 +0200 Subject: [PATCH 2/2] from&until more OAI2.0 compl., adding tfs --- .../plugin/oai/OaiCollectorPlugin.java | 4 +- .../collection/plugin/oai/OaiIterator.java | 4 +- ...c_cleaning_OPENAIREplus_compliant_hal_orig | 143 +++++ ..._cleaning_OpenAIREplus_compliant_doaj_orig | 140 +++++ .../xslt_cleaning_datarepo_datacite_orig.xsl | 0 ...e_datacite_ExchangeLandingpagePid_orig.xsl | 0 .../original/xslt_nlm2oaf_journal.fi_orig.xsl | 492 +++++++++++++++++ .../original/xslt_nlm2oaf_us-pmc_orig.xsl | 437 ++++++++++++++++ .../scripts/xslt_nlm2oaf_journal.fi.xsl | 493 ++++++++++++++++++ .../transform/scripts/xslt_nlm2oaf_us-pmc.xsl | 373 +++++++++++++ 10 files changed, 2082 insertions(+), 4 deletions(-) create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OPENAIREplus_compliant_hal_orig create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OpenAIREplus_compliant_doaj_orig rename dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/{ => original}/xslt_cleaning_datarepo_datacite_orig.xsl (100%) rename dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/{ => original}/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid_orig.xsl (100%) create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_journal.fi_orig.xsl create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_us-pmc_orig.xsl create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_journal.fi.xsl create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_us-pmc.xsl diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiCollectorPlugin.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiCollectorPlugin.java index 4600562ca..67fd352a3 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiCollectorPlugin.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiCollectorPlugin.java @@ -62,11 +62,11 @@ public class OaiCollectorPlugin implements CollectorPlugin { throw new CollectorException("Param 'mdFormat' is null or empty"); } - if (fromDate != null && !fromDate.matches("\\d{4}-\\d{2}-\\d{2}")) { + if (fromDate != null && !fromDate.matches("\\d{4}-\\d{2}-\\d{2}") && !fromDate.matches("\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}Z")) { throw new CollectorException("Invalid date (YYYY-MM-DD): " + fromDate); } - if (untilDate != null && !untilDate.matches("\\d{4}-\\d{2}-\\d{2}")) { + if (untilDate != null && !untilDate.matches("\\d{4}-\\d{2}-\\d{2}") && !untilDate.matches("\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}Z")) { throw new CollectorException("Invalid date (YYYY-MM-DD): " + untilDate); } diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiIterator.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiIterator.java index 12d313108..c044e02db 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiIterator.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/oai/OaiIterator.java @@ -107,10 +107,10 @@ public class OaiIterator implements Iterator { if (set != null && !set.isEmpty()) { url += "&set=" + URLEncoder.encode(set, "UTF-8"); } - if (fromDate != null && fromDate.matches("\\d{4}-\\d{2}-\\d{2}")) { + if (fromDate != null && (fromDate.matches("\\d{4}-\\d{2}-\\d{2}") || fromDate.matches("\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}Z"))) { url += "&from=" + URLEncoder.encode(fromDate, "UTF-8"); } - if (untilDate != null && untilDate.matches("\\d{4}-\\d{2}-\\d{2}")) { + if (untilDate != null && (untilDate.matches("\\d{4}-\\d{2}-\\d{2}") || untilDate.matches("\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}Z"))) { url += "&until=" + URLEncoder.encode(untilDate, "UTF-8"); } log.info("Start harvesting using url: " + url); diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OPENAIREplus_compliant_hal_orig b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OPENAIREplus_compliant_hal_orig new file mode 100644 index 000000000..d4eb71dc4 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OPENAIREplus_compliant_hal_orig @@ -0,0 +1,143 @@ +// from PROD 2021-07-06 , tf script of HAL with around 3mill. records +declare_script "dc_cleaning_OpenAIREplus_compliant_hal"; +declare_ns oaf = "http://namespace.openaire.eu/oaf"; +declare_ns dri = "http://www.driver-repository.eu/namespace/dri"; +declare_ns dr = "http://www.driver-repository.eu/namespace/dr"; +declare_ns dc = "http://purl.org/dc/elements/1.1/"; +declare_ns prov = "http://www.openarchives.org/OAI/2.0/provenance"; +declare_ns oai = "http://www.openarchives.org/OAI/2.0/"; +declare_ns xs = "http://www.w3.org/2001/XMLSchema"; +$var0 = "''"; +$varFP7 = "'corda_______::'"; +$varH2020 = "'corda__h2020::'"; +$varDummy = "''"; +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"]); +static $varRepoid = xpath:"//dri:repositoryId"; +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"]); +dri:objIdentifier = xpath:"//dri:objIdentifier"; +dri:repositoryId = $varRepoid; +dri:recordIdentifier = xpath:"//dri:recordIdentifier"; +// +// communities - deactivated until received green light from DARIAH to mark community on prod also +// $varCommunity = xpath:"//*[local-name()='setSpec'][starts-with(., 'collection:DARIAH')]/'dariah'"; +// concept should not appear with empty attribute id, i.e when there is no community - ugly, but seems to work (oaf:datasourceprefix = just any field available in all records) +// oaf:concept = set(xpath:"//oaf:datasourceprefix[string-length($varCommunity) gt 0]/''", @id = $varCommunity;); +// +// apply xpath:"//dc:contributor[starts-with(., 'European Project')]" if xpath:"string-length(replace(., '.*(\d{6,6}).*', '$1')) = 6" oaf:projectid = xpath:"concat($var1, replace(., '.*(\d{6,6}).*', '$1'))"; else $varDummy = "''"; +apply xpath:"//dc:creator" if xpath:"string-length(.) > 0 and normalize-space(.) != ','" dc:creator = xpath:"normalize-space(.)"; else $varDummy = "''"; +if xpath:"//dc:title[string-length(.)> 0]" $varDummy = "''"; else dc:coverage = skipRecord(); +dc:title = xpath:"//dc:title[string-length(.) > 0]/normalize-space(.)"; +apply xpath:"//dc:subject" if xpath:"string-length(.) > 0" dc:subject = xpath:"normalize-space(.)"; else $varDummy = "''"; +apply xpath:"//dc:publisher" if xpath:"string-length(.) > 0" dc:publisher = xpath:"normalize-space(.)"; else $varDummy = "''"; +apply xpath:"//dc:source" if xpath:"string-length(.) > 0" dc:source = xpath:"normalize-space(.)"; else $varDummy = "''"; +dc:contributor = xpath:"//dc:contributor"; +// dc:description = xpath:"//dc:description/normalize-space(.)"; +//dc:description = xpath:"string-join(//dc:description/normalize-space(.), concat('; ',codepoints-to-string(10)))"; +dc:description = xpath:"string-join(//dc:description/normalize-space(.), '; ')"; +dc:format = xpath:"//dc:format"; +$varHttpTest = "''"; +oaf:fulltext = xpath:"//dc:identifier[starts-with(., 'http') and (ends-with(., 'document') or ends-with(., 'pdf'))]"; +//if xpath:"//dc:identifier[starts-with(., 'http') and (ends-with(., 'document') or ends-with(., 'pdf'))] or //dc:relation[starts-with(lower-case(normalize-space(.)), 'info:eu-repo/grantagreement')] or //dc:rights[starts-with(lower-case(normalize-space(.)), 'open') or contains(lower-case(normalize-space(.)), 'openaccess')] or //dc:accessRights[contains(lower-case(normalize-space(.)), 'openaccess')]" $var0 = "''"; else dc:coverage = skipRecord(); +if xpath:"//dc:identifier[starts-with(., 'http')]" $var0 = "''"; else dc:coverage = skipRecord(); +apply xpath:"//dc:identifier" if xpath:"starts-with(normalize-space(.), 'http')" dc:identifier = xpath:"normalize-space(.)"; else dr:CobjIdentifier = xpath:"normalize-space(.)"; +dr:dateOfCollection = xpath:"//dri:dateOfCollection"; +static dr:dateOfTransformation = xpath:"current-dateTime()"; +dc:type = xpath:"//dc:type"; +dc:format = xpath:"//dc:format"; +dc:date = xpath:"//dc:date"; +dc:language = Convert(xpath:"//dc:language", Languages); +$varDateAccepted = Convert(xpath:"descendant-or-self::dc:date", DateISO8601, "yyyy-MM-dd", "min()"); +if xpath:"starts-with($varDateAccepted, '0')" oaf:dateAccepted = $varDummy; else oaf:dateAccepted = $varDateAccepted; +$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')"; +oaf:embargoenddate = $varEmbargoEnd; +// FP7 +oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')][year-from-date(xs:date(max(($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)(.*)', '$3', 'i')))"; +// H2020 +oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')][year-from-date(xs:date(max(($varDateAccepted, '0001-01-01')))) gt 2012][contains(lower-case(.), 'info:eu-repo')]/concat($varH2020, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement[/]+ec/h2020/)(\d\d\d\d\d\d)(.*)', '$3', 'i')))"; +// H2020 workaround for HAL +oaf:projectid = xpath:"distinct-values(//dc:relation[matches(normalize-space(.), '(.*)(info:eu-repo/grantagreement//)(\d\d\d\d\d\d)(.*)', 'i')][//dc:contributor[contains(lower-case(.), 'h2020')]][year-from-date(xs:date(max(($varDateAccepted, '0001-01-01')))) gt 2012][contains(lower-case(.), 'info:eu-repo')]/concat($varH2020, replace(normalize-space(.), '(.*)(info:eu-repo/grantagreement//)(\d\d\d\d\d\d)(.*)', '$3', 'i')))"; +dc:relation = xpath:"//dc:relation"; +//comment-js-09-10-2012 apply xpath:"//dc:rights" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/semantics')" dc:rights = empty; else dc:rights = xpath:"normalize-space(.)"; +// +oaf:collectedDatasourceid = xpath:"$varDatasourceid"; +// +//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); +$varCobjCategoryReverse = Convert(xpath:"insert-before(reverse(//dc:type) , 0, reverse(//oai:setSpec))", TextTypologies); +$varSuperTypeReverse = Convert(xpath:"normalize-space($varCobjCategoryReverse)", SuperTypes); +dr:CobjCategory = set(xpath:"//oaf:datasourceprefix[//dc:type[1]/lower-case(.) = ('text', 'info:eu-repo/semantics/other', 'other') or //oaf:datasourceprefix/lower-case(.) = 'openedition_']/$varCobjCategoryReverse", @type = $varSuperTypeReverse;); +$varCobjCategoryStraight = Convert(xpath:"insert-before(//dc:type , 100, //oai:setSpec)", TextTypologies); +$varSuperTypeStraight = Convert(xpath:"normalize-space($varCobjCategoryStraight)", SuperTypes); +dr:CobjCategory = set(xpath:"//oaf:datasourceprefix[not(//dc:type[1]/lower-case(.) = ('text', 'info:eu-repo/semantics/other', 'other'))]/$varCobjCategoryStraight", @type = $varSuperTypeStraight;); +// +// review level +// oaf:refereed = Convert(xpath:"//dc:description", ReviewLevels); +$varRefereedConvt = Convert(xpath:"(//dc:type, //oai:setSpec, //dc:description)", ReviewLevels); +$varRefereedDesct = xpath:"(//dc:description[matches(lower-case(.), '.*(this\s*book|it)\s*constitutes\s*the\s*(thoroughly\s*)?refereed') or matches(lower-case(.), '.*peer[\.\-_/\s\(\)]?review\s*under\s*responsibility\s*of.*')]/'0001', //dc:description[matches(., '^version\s*(préliminaire.*|0$)')]/'0002')"; +$varRefereedIdntf = xpath:"(//*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)])pre[\.\-_/\s\(\)]?prints?([\.\-_/\s\(\)].*)?$')][count(//dc:identifier) = 1]/'0002', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)])refereed([\.\-_/\s\(\)\d].*)?$')]/'0001', //*[string(node-name(.)) = 'dc:identifier' and contains(lower-case(.), '-peer-reviewed-article-')]/'0001')"; +$varRefereed = xpath:"($varRefereedConvt, $varRefereedIdntf, $varRefereedDesct)"; +if xpath:"count(index-of($varRefereed, '0001')) >0" oaf:refereed = xpath:"'0001'"; else $varDummy= "''"; +if xpath:"count(index-of($varRefereed, '0002')) >0 and count(index-of($varRefereed, '0001')) = 0" oaf:refereed = xpath:"'0002'"; else $varDummy= "''"; +// +apply xpath:"//dc:rights" if xpath:"starts-with(normalize-space(.), 'info:eu-repo/semantics') and (xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) gt current-date())" oaf:accessrights = Convert(xpath:"normalize-space(.)", AccessRights); else dc:rights = xpath:"."; +// 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:"."; +//2021-06-01 ; acz ; next line to avoid to be OPEN as default, set to UNKNOWN , 2021-07-05 acz +//if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics') and not(xs:date( max( ($varEmbargoEnd, '0001-01-01') ) ) lt current-date())]" $var0 = "''"; else oaf:accessrights = "UNKNOWN"; +oaf:license = xpath:"//dc:rights[starts-with(., 'http') or matches(., '^CC[- ]BY([- ](NC([- ](ND|SA))?|ND|SA))([- ]\d(\.\d)?)?$', 'i')]"; +// +static oaf:collectedFrom = set("''", @name = $varOfficialname; , @id = $varDatasourceid;); +static oaf:hostedBy = set("''", @name = $varOfficialname; , @id = $varDatasourceid;); +// +//$varId = identifierExtract('["//dc:identifier", "//dc:relation"]' , xpath:"./*[local-name()='record']" , '(10[.][0-9]{4,}[^\s"/<>]*/[^\s"<>]+)'); +$varIdDoi = identifierExtract('["//dc:identifier[starts-with(., \"info:\") or starts-with(., \"urn:\") or starts-with(., \"doi:\") or starts-with(., \"DOI:\") or starts-with(., \"Doi:\") or starts-with(., \"doi \") or starts-with(., \"DOI \") or starts-with(., \"Doi \") or starts-with(., \"10.\") or ((starts-with(., \"http\")) and contains(., \"doi.org/10.\"))]", "//dc:relation[starts-with(., \"info:eu-repo/semantics/altIdentifier/doi/10.\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/DOI/10.\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/Doi/10.\") or ((starts-with(., \"info:eu-repo/semantics/altIdentifier/url/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/purl/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/urn/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/doi/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/DOI/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/Doi/http\")) and contains(., \"doi.org/10.\"))]"]' , xpath:"./*[local-name()='record']" , '(10[.][0-9]{4,}[^\s"/<>]*/[^\s"<>]+)'); + +$varIdHdl = identifierExtract('["//dc:identifier[starts-with(., \"HDL:\") and not(starts-with(., \"HDL: http\"))][not(contains(., \"123456789\"))]", "//dc:relation[starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/hdl/\") or (starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/url/\") and contains(., \"://hdl.handle.net/\"))]"]' , xpath:"./*[local-name()='record']" , '(?!(info:hdl:|://hdl.handle.net/|info:eu-repo/semantics/altIdentifier/hdl/))(\d.*)'); + + +$varIdIsbn = xpath:"(//dc:identifier, //dc:source)[starts-with(lower-case(.), 'isbn') or starts-with(., '978') or starts-with(., '979')][(matches(., '(isbn[:\s]*)?97[89]-\d+-\d+-\d+-\d+$', 'i') and string-length(concat('97', substring-after(., '97'))) = 17) or matches(., '(isbn[:\s]*)?97[89]\d{10}$', 'i')]/replace(., 'isbn[:\s]*', '', 'i'), //dc:relation[starts-with(lower-case(.), 'info:eu-repo/semantics/altidentifier/isbn/')][(matches(., 'info:eu-repo/semantics/altIdentifier/isbn/97[89]-\d+-\d+-\d+-\d+$', 'i') and string-length(.) = 59) or matches(., 'info:eu-repo/semantics/altidentifier/isbn/97[89]\d{10}$', 'i')]/substring-after(lower-case(.), 'info:eu-repo/semantics/altidentifier/isbn/')"; + +$varIdBibc = identifierExtract('["//dc:identifier[starts-with(., \"BibCode:\") or starts-with(., \"BIBCODE:\") or (starts-with(., \"http:\") and contains(., \"bibcode=\"))]"]' , xpath:"./*[local-name()='record']" , '(^(BibCode:|BIBCODE:|http).*$)'); + +$varIdPtnt = identifierExtract('["//dc:identifier[starts-with(., \"Patent N°:\")]"]' , xpath:"./*[local-name()='record']" , '(^Patent N°:.*$)'); + +$varPmId = identifierExtract('["//dc:identifier[starts-with(normalize-space(.), \"PUBMED:\")]"]' , xpath:"./*[local-name()='record']" , '(?!PUBMED: )(\d+)'); + +$varIdPmc = identifierExtract('["//dc:identifier[starts-with(., \"PUBMEDCENTRAL:\") or (starts-with(., \"http\") and contains(., \"://www.ncbi.nlm.nih.gov/pmc/articles/PMC\"))]", "//dc:relation[starts-with(., \"info:eu-repo/semantics/altIdentifier/pmid/PMC\") or ((starts-with(., \"info:eu-repo/semantics/altIdentifier/url/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/purl/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/urn/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/pmid/http\")) and contains(., \"://www.ncbi.nlm.nih.gov/pmc/articles/PMC\"))]"]' , xpath:"./*[local-name()='record']" , '(PMC\d+)'); + +//$varIdHal = identifierExtract('["//dc:identifier[starts-with(., \"ads-\") or starts-with(., \"anses-\") or starts-with(., \"artxibo-\") or starts-with(., \"bioemco-\") or starts-with(., \"cea-\") or starts-with(., \"cel-\") or starts-with(., \"cirad-\") or starts-with(., \"edutice-\") or starts-with(., \"emse-\") or starts-with(., \"EMSE-\") or starts-with(., \"ensl-\") or starts-with(., \"hal-\") or starts-with(., \"HAL-\") or starts-with(., \"halsde-\") or starts-with(., \"halshs-\") or starts-with(., \"hprints-\") or starts-with(., \"in2p3-\") or starts-with(., \"ineris-\") or starts-with(., \"inria-\") or starts-with(., \"Inria-\") or starts-with(., \"inserm-\") or starts-with(., \"insu-\") or starts-with(., \"INSU-\") or starts-with(., \"ird-\") or starts-with(., \"irsn-\") or starts-with(., \"jpa-\") or starts-with(., \"lirmm-\") or starts-with(., \"medihal-\") or starts-with(., \"meteo-\") or starts-with(., \"mnhn-\") or starts-with(., \"obspm-\") or starts-with(., \"pastel-\") or starts-with(., \"pasteur-\") or starts-with(., \"Pasteur-\") or starts-with(., \"peer-\") or starts-with(., \"ssa-\") or starts-with(., \"tel-\") or starts-with(., \"ujm-\") or starts-with(., \"ijn_\") or starts-with(., \"sic_\") or (starts-with(., \"http\") and (contains(., \"://hal.archives-ouvertes.fr/hal\") or contains(., \"://halshs.archives-ouvertes.fr/hal\") or contains(., \"://halsde.archives-ouvertes.fr/hal\") or contains(., \"://medihal.archives-ouvertes.fr/hal\")))]", "//dc:relation[((starts-with(., \"info:eu-repo/semantics/altIdentifier/url/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/purl/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/urn/http\")) and (contains(., \"://hal.archives-ouvertes.fr/hal\") or contains(., \"://halshs.archives-ouvertes.fr/hal\") or contains(., \"://halsde.archives-ouvertes.fr/hal\")))]"]' , xpath:"./*[local-name()='record']" , '((ads|anses|artxibo|bioemco|cea|cel|cirad|edutice|emse|EMSE|ensl|hal|HAL|halsde|halshs|hprints|in2p3|ineris|inria|Inria|inserm|insu|INSU|ird|irsn|jpa|lirmm|medihal|meteo|mnhn|obspm|pastel|pasteur|Pasteur|peer|ssa|tel|ujm)-|(ijn|sic)_).*'); +$varIdHal = identifierExtract('["//*[local-name() = \"recordIdentifier\"]"]' , xpath:"./*[local-name()='record']" , '(oai:HAL:.*)'); + +$varIdArxv = identifierExtract('["//dc:identifier[((starts-with(., \"http\") or starts-with(., \"ArXiv: http\")) and (contains(., \"://arxiv.org/abs/\") or contains(., \"://arxiv.org/pdf/\"))) or starts-with(., \"arXiv:\") or starts-with(., \"ARXIV:\")]", "//dc:relation[(starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/arxiv/\") and not(contains(., \"/arxiv/http\"))) or ((starts-with(., \"info:eu-repo/semantics/altIdentifier/url/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/purl/http\") or starts-with(., \"info:eu-repo/semantics/altIdentifier/urn/http\") or starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/arxiv/http\")) and (contains(., \"://arxiv.org/abs/\") or contains(., \"://arxiv.org/pdf/\")))]"]' , xpath:"./*[local-name()='record']" , '(?!(://arxiv.org/abs/|:eu-repo/semantics/altIdentifier/arxiv/))([a-zA-Z].*)'); + +$varIdWos = identifierExtract('["//dc:identifier[starts-with(., \"WOS:\") or starts-with(., \"wos: WOS:\")]", "//dc:relation[starts-with(normalize-space(.), \"info:eu-repo/semantics/altIdentifier/wos/\")]"]' , xpath:"./*[local-name()='record']" , '(info.*|WOS:.+|wos: WOS:.+)'); + +//oaf:identifier = set(xpath:"$varId//value[not[. = '10.1145/nnnnnnn.nnnnnnn']]", @identifierType = "doi";); +oaf:identifier = set(xpath:"$varIdDoi//value[not(. = '10.1145/nnnnnnn.nnnnnnn')]", @identifierType = "doi";); +oaf:identifier = set(xpath:"$varIdHdl//value", @identifierType = "handle";); +oaf:identifier = set(xpath:"$varIdIsbn", @identifierType = "isbn";); + +oaf:identifier = set(xpath:"($varIdBibc//value[not(starts-with(., 'http'))]/replace(., 'BIBCODE:\s*', ''), $varIdBibc//value[starts-with(., 'http') and contains(substring-after(., 'bibcode='), codepoints-to-string(38))]/substring-before(substring-after(., 'bibcode='), codepoints-to-string(38)), $varIdBibc//value[starts-with(., 'http') and not(contains(substring-after(., 'bibcode='), codepoints-to-string(38)))]/substring-after(., 'bibcode='))", @identifierType = "bibcode";); + +oaf:identifier = set(xpath:"$varIdPtnt//value/normalize-space(substring-after(., 'Patent N°:'))", @identifierType = "patentNumber";); + +oaf:identifier = set(xpath:"$varPmId//value", @identifierType = "pmid";); +oaf:identifier = set(xpath:"$varIdPmc//value", @identifierType = "pmcid";); +//oaf:identifier = set(xpath:"distinct-values($varIdHal//value/replace(., '(/document|/image|/file/.*)$', ''))", @identifierType = "hal";); +oaf:identifier = set(xpath:"distinct-values($varIdHal//value/replace(substring-after(., 'oai:HAL:'), '(v\d*)$', ''))", @identifierType = "hal";); +oaf:identifier = set(xpath:"distinct-values(($varIdArxv//value/normalize-space(replace(., '(https?://arxiv.org/abs/|https?://arxiv.org/pdf/|info:eu-repo/semantics/altIdentifier/arxiv/|info:eu-repo/semantics/altIdentifier/url/|info:eu-repo/semantics/altIdentifier/urn/|arXiv:|\.pdf)', '', 'i'))))", @identifierType = "arxiv";); +oaf:identifier = set(xpath:"$varIdWos//value/normalize-space(replace(., '(info:eu-repo/semantics/altIdentifier/wos/|WOS:|wos:)', ''))", @identifierType = "wos";); + +oaf:identifier = set(xpath:"distinct-values(//dc:identifier[starts-with(., 'http') and contains(., $varIdHal//value/replace(substring-after(., 'oai:HAL:'), '(v\d*)$', ''))]/replace(., '(/document|/image|/file/.*)$', ''))", @identifierType = "landingPage";); +oaf:identifier = set(xpath:"distinct-values(//dc:identifier[starts-with(., 'http') and not(ends-with(., $varIdHal//value/replace(substring-after(., 'oai:HAL:'), '(v\d*)$', '')))])", @identifierType = "url";); + +oaf:identifier = set(xpath:"//dri:recordIdentifier", @identifierType = "oai-original";); + +oaf:datasourceprefix = xpath:"//oaf:datasourceprefix"; + +// journal data +// avoiding regular expressions, while a) correcting ISSNs with no - or other letters instead of - and b) ignoring any stuff after the ISSN (as e.g. print/online/...) +$varISSN = xpath:"//dc:source[starts-with(., 'ISSN:') and string-length(.) > 12]/concat(substring(normalize-space(substring-after(., 'ISSN:')), 1, 4), '-', normalize-space(substring-after(., substring(normalize-space(substring-after(., 'ISSN:')), 1, 4))))"; +//$varEISSN = xpath:"//dc:source[starts-with(., 'EISSN:') and string-length(.) > 13]/normalize-space(substring-after(., 'ISSN:'))"; +$varEISSN = xpath:"//dc:source[starts-with(., 'EISSN:') and string-length(.) > 13]/concat(substring(normalize-space(substring-after(., 'EISSN:')), 1, 4), '-', normalize-space(substring-after(., substring(normalize-space(substring-after(., 'EISSN:')), 1, 4))))"; +oaf:journal = set(xpath:"//oaf:datasourceprefix[$varISSN or $varEISSN]/''", @issn = xpath:"$varISSN";, @eissn = xpath:"$varEISSN";); + +end diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OpenAIREplus_compliant_doaj_orig b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OpenAIREplus_compliant_doaj_orig new file mode 100644 index 000000000..f8bc42a2c --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/dc_cleaning_OpenAIREplus_compliant_doaj_orig @@ -0,0 +1,140 @@ +// from PROD 2021-07-06 , tf script of DOAJ with more than 6mill. records +declare_script "dc_cleaning_OpenAIREplus_compliant_doaj"; +declare_ns oaf = "http://namespace.openaire.eu/oaf"; +declare_ns dri = "http://www.driver-repository.eu/namespace/dri"; +declare_ns dr = "http://www.driver-repository.eu/namespace/dr"; +declare_ns dc = "http://purl.org/dc/elements/1.1/"; +declare_ns prov = "http://www.openarchives.org/OAI/2.0/provenance"; +$var0 = "''"; +$varFP7 = "'corda_______::'"; +$varH2020 = "'corda__h2020::'"; +$varDummy = "''"; +// $varUnknownRepoId = "'openaire____::55045bd2a65019fd8e6741a755395c8c'"; +// +$varUnknownRepoId = "'openaire____::1256f046-bf1f-4afc-8b47-d0b147148b18'"; +$varUnknownRepoName = "'Unknown Repository'"; +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"]); +static $varRepoid = xpath:"//dri:repositoryId"; +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"]); +dri:objIdentifier = xpath:"//dri:objIdentifier"; +dri:repositoryId = $varRepoid; +dri:recordIdentifier = xpath:"//dri:recordIdentifier"; + +if xpath:"//dc:creator[string-length(normalize-space(.)) &gt; 0][contains(., 'CDATA')][starts-with(normalize-space(.), '(')][starts-with(normalize-space(.), '.')]" dc:creator = skipRecord(); else $varDummy = "''"; +//apply xpath:"//dc:creator" if xpath:"string-length(normalize-space(.)) &amp;gt; 0 and not(contains(., 'CDATA')) and not(starts-with(normalize-space(.), '.')) and not(starts-with(normalize-space(.), '('))" dc:creator = Convert(xpath:".", Person); else $varDummy = "''"; +if xpath:"count(//dc:creator) = 0" dc:creator = skipRecord(); else $varDummy = "''"; +//apply xpath:"//dc:creator" if xpath:"string-length(.) &gt; 0 and normalize-space(.) != ','" dc:creator = xpath:"normalize-space(.)"; else $varDummy = "''"; +$varOrcidName = xpath:"//dc:creator[string-length(normalize-space(.)) > 0]"; +$varOrcidOrcid = xpath:"//dc:creator[string-length(normalize-space(.)) > 0]/@id/replace(., 'https?://orcid.org/', '')"; +dc:creator = set(xpath:"$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/')";); + +if xpath:"count(//dc:title[string-length(.) &gt; 0]) = 0" dc:title = skipRecord(); else $varDummy = "''"; +dc:title = xpath:"//dc:title/normalize-space(replace(., '^(&lt;title language=)(.)*(&gt;)', ''))"; +// apply xpath:"//dc:title" if xpath:"string-length(.) &gt; 0" dc:title = xpath:"normalize-space(.)"; else $varDummy = "''"; + +apply xpath:"//dc:subject" if xpath:"string-length(.) &gt; 0 and not(@xsi:type = 'dcterms:LCSH')" dc:subject = xpath:"normalize-space(.)"; else $varDummy = "''"; +dc:subject = set(xpath:"//dc:subject[@xsi:type = 'dcterms:LCSH']/concat('lcsh:', .)", @classid=xpath:"'lcsh'";, @classname=xpath:"'lcsh'";, @schemeid=xpath:"'dnet:subject_classification_typologies'";, @schemename=xpath:"'dnet:subject_classification_typologies'";); + +apply xpath:"//dc:publisher" if xpath:"string-length(.) &gt; 0" dc:publisher = xpath:"normalize-space(replace(., '(&lt;br&gt;)', ''))"; else $varDummy = "''"; +apply xpath:"//dc:source" if xpath:"string-length(.) &gt; 0" dc:source = xpath:"normalize-space(.)"; else $varDummy = "''"; +dc:contributor = xpath:"//dc:contributor"; +dc:description = xpath:"//dc:description[not(starts-with(., 'URN: urn:nbn:') or starts-with(., 'URN: http'))]"; +dc:format = xpath:"//dc:format"; +$varHttpTest = "''"; +if xpath:"//dc:relation[starts-with(., 'http') or starts-with(., 'www.')]" $varHttpTest = "true"; else dc:identifier = skipRecord(); +//apply xpath:"//dc:relation" if xpath:"starts-with(normalize-space(.), 'http')" dc:identifier = xpath:"normalize-space(.)"; else dr:CobjIdentifier = xpath:"normalize-space(.)"; +//apply xpath:"//dc:relation" if xpath:"starts-with(normalize-space(.), 'www.')" dc:identifier = xpath:"concat('http://', normalize-space(.))"; else dr:CobjIdentifier = xpath:"normalize-space(.)"; +dr:CobjIdentifier = xpath:"distinct-values(//dc:identifier[not(starts-with(normalize-space(.), 'http'))][not(normalize-space(.) = ($varIdList))][not(starts-with(normalize-space(.), 'urn:nbn:') or starts-with(normalize-space(.), 'URN:NBN:'))][not(. = ($varISSN[1], $varISSN[2]))][normalize-space(.) != ''])"; +dc:identifier = xpath:"($varIdUrl//value[not(starts-with(., 'www'))], $varIdUrl//value[starts-with(., 'www')]/concat('http://', .), $varIdLdpg//value, $varIdDoi//value)[1]"; +dc:relation = xpath:"//dc:relation[starts-with(., 'https://doaj.org/toc/')]"; + +dr:dateOfCollection = xpath:"//dri:dateOfCollection"; +static dr:dateOfTransformation = xpath:"current-dateTime()"; +// dc:type = xpath:"//dc:type"; +dc:language = Convert(xpath:"//dc:language", Languages); +//if xpath:"//dc:rights[text()='info:eu-repo/semantics/openAccess']" dc:publisher = xpath:"//dc:publisher"; else dc:publisher = skipRecord(); +dc:date = xpath:"//dc:date"; +oaf:dateAccepted = Convert(xpath:"descendant-or-self::dc:date", DateISO8601, "yyyy-MM-dd", "min()"); +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 = "''"; +//apply xpath:"//dc:relation" if xpath:"string-length(substring-after(normalize-space(.), 'info:eu-repo/grantAgreement/EC/FP7/')) = 6" oaf:projectid = RegExpr(xpath:"normalize-space(.)", $var1, "s/^(.*info:eu-repo\/grantAgreement\/EC\/FP7\/)//gmi"); else dc:relation = xpath:"normalize-space(.)"; +//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(.)"; +// +oaf:collectedDatasourceid = $varDatasourceid; +// +// apply xpath:"//dc:type" if xpath:"." dr:CobjCategory = Convert(xpath:"normalize-space(.)", TextTypologies); else dc:type = xpath:"."; +//dr:CobjCategory = "0001"; +$varCobjCategory = Convert(xpath:"//dc:type", TextTypologies); +$varSuperType = Convert(xpath:"normalize-space($varCobjCategory)", SuperTypes); +dr:CobjCategory = set($varCobjCategory, @type = $varSuperType;); +dc:type = xpath:"//dc:type"; +// +// review status + +$varRefereedIdntf = xpath:"(//*[string(node-name(.)) = 'dc:identifier' and matches(., '^(https?://(dx\.)?doi.org/)?10\.12688/(f1000research|wellcomeopenres|aasopenres|gatesopenres|hrbopenres)\.\d*(\.\d*|-\d*\.v\d*)$')]/'0001', //*[string(node-name(.)) = 'dc:relation' and matches(., '^info:eu-repo/semantics/altIdentifier/doi/10\.12688/(f1000research|wellcomeopenres|aasopenres|gatesopenres|hrbopenres)\.\d*(\.\d*|-\d*\.v\d*)$', 'i')]/'0001')"; + +$varRefereedProse = xpath:"(//*[string(node-name(.)) = 'dc:description' and matches(lower-case(.), '.*this\s*preprint\s*has\s*been\s*reviewed\s*and\s*recommended\s*by\s*peer\s*community') and contains(., '10.24072/')]/'0001', //dc:title[matches(lower-case(.), '.*\[.*peer[\s\-\._]*review\s*:.*\]\s*$')]/'0001')"; +$varRefereedReltn = xpath:"(//dc:relation, //dc:identifier)[contains(., '://www.dovepress.com/') and matches(lower-case(.), '.*-peer-reviewed-(fulltext-)?article-.*')]/'0001'"; +$varRefereedTitle = xpath:"//dc:title[matches(lower-case(.), '.*\[.*peer[\s\-\._]*review\s*:.*\]\s*$')]/'0001'"; +$varRefereedDesct = xpath:"(//dc:description[matches(lower-case(.), '.*peer[\.\-_/\s\(\)]?review\s*under\s*responsibility\s*of.*') or matches(lower-case(.), '(this|a)\s*(article|preprint)\s*(has\s*been\s*)?(peer[\-\s]*)?reviewed\s*and\s*recommended\s*by\s*peer[\-\s]*community')]/'0001')"; +$varRefereed = xpath:"($varRefereedIdntf, $varRefereedProse, $varRefereedReltn, $varRefereedTitle, $varRefereedDesct)"; +//if xpath:"$varRefereed" oaf:refereed = xpath:"'0001'"; else $varDummy= "''"; +if xpath:"count(index-of($varRefereed, '0001')) >0" oaf:refereed = xpath:"'0001'"; else $varDummy= "''"; +if xpath:"count(index-of($varRefereed, '0002')) >0 and count(index-of($varRefereed, '0001')) = 0" oaf:refereed = xpath:"'0002'"; else $varDummy= "''"; +// +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:"."; +if xpath:"//dc:rights[starts-with(normalize-space(.), 'info:eu-repo/semantics')]" $var0 = "''"; else oaf:accessrights = "OPEN"; +//if xpath:"count(//dc:rights) = 0" oaf:accessrights = "OPEN"; else $var0 = "''"; +// oaf:accessrights = Convert(xpath:"normalize-space(//dc:rights)", AccessRights); +oaf:license = xpath:"(//dc:rights, //dc:relation)[starts-with(normalize-space(.), 'http') and (contains(., '/licenses/') or contains(., '/licence/') or contains(., '/licencias/') or contains(., '/licencia/') or contains(., '://creativecommons.org/') or contains(., '://rightsstatements.org/')) or matches(., '^CC[- ]BY([- ](NC([- ](ND|SA))?|ND|SA))([- ]\d(\.\d)?)?$', 'i')][not(contains(normalize-space(.), ' '))]/normalize-space(.)"; +// +static oaf:collectedFrom = set("''", @name = $varOfficialname; , @id = $varDatasourceid;); +static oaf:hostedBy = set("''", @name = $varOfficialname; , @id = $varDatasourceid;); +// +//$varId = identifierExtract('["//dc:identifier", "//dc:relation"]' , xpath:"./*[local-name()='record']" , '(10[.][0-9]{4,}[^\s"/&lt;&gt;]*/[^\s"&lt;&gt;]+)'); +$varIdDoi = identifierExtract('["//dc:identifier[starts-with(., \"10.\") or starts-with(., \"DOI:\") or starts-with(., \"doi:\") or (starts-with(., \"http\") and contains(., \"doi.org/\"))]", "//dc:relation[starts-with(., \"10.\") or starts-with(., \"DOI:\") or starts-with(., \"doi:\") or (starts-with(., \"http\") and contains(., \"doi.org/\"))]"]' , xpath:"./*[local-name()='record']" , '(10[.][0-9]{4,}[^\s"/<>]*/[^\s"<>]+)'); +$varIdHdl = identifierExtract('["//dc:relation[starts-with(., \"http\") and contains(., \"://hdl.handle.net/\")][not(contains(., \"123456789\"))]"]' , xpath:"./*[local-name()='record']" , '(?!(://hdl.handle.net/))(\d.*)'); +$varIdUrn = identifierExtract('["//dc:relation[starts-with(., \"urn:nbn:\") or starts-with(., \"URN:NBN:\") or (starts-with(., \"http\") and (contains(., \"://nbn-resolving.org/urn:nbn:\") or contains(., \"://nbn-resolving.de/urn/resolver.pl?urn:nbn:\") or contains(., \"://nbn-resolving.de/urn:nbn:\") or contains(., \"://resolver.obvsg.at/urn:nbn:\") or contains(., \"://urn.fi/URN:NBN:\") or contains(., \"://urn.kb.se/resolve?urn=urn:nbn:\")))]", "//dc:description[contains(., \"URN: urn:nbn:de:0114-\") or contains(., \"URN: http://nbn-resolving.de/urn:nbn:de:0114-\") or (contains(., \"URN:NBN:no-\") and //dc:identifier = \"1893-1774\")]"]' , xpath:"./*[local-name()='record']" , '((urn:nbn:|URN:NBN:).*)'); +$varIdArk = identifierExtract('["//dc:relation[starts-with(normalize-space(.), \"http\") and contains(., \"/ark:\")]"]' , xpath:"./*[local-name()='record']" , '(http.*)'); +$varIdPmid = identifierExtract('["//dc:relation[starts-with(., \"http\") and contains(., \"://www.ncbi.nlm.nih.gov/pmc/articles/pmid/\")]"]' , xpath:"./*[local-name()='record']" , '(http.*)'); +$varIdPmc = identifierExtract('["//dc:relation[starts-with(., \"http\") and (contains(., \"://www.ncbi.nlm.nih.gov/pmc/articles/PMC\") or contains(., \"//europepmc.org/articles/PMC\"))]"]' , xpath:"./*[local-name()='record']" , '(http.*)'); +$varIdHal = identifierExtract('["//dc:relation[starts-with(., \"hal-\") or starts-with(., \"halshs-\") or starts-with(., \"halsde-\") or (starts-with(., \"http\") and (contains(., \"://hal.archives-ouvertes.fr/hal\") or contains(., \"://halshs.archives-ouvertes.fr/hal\") or contains(., \"://halsde.archives-ouvertes.fr/hal\")))]"]' , xpath:"./*[local-name()='record']" , '(hal(shs|sde)?-.*)'); +$varIdArxv = identifierExtract('["//dc:relation[starts-with(., \"http\") and (contains(., \"://arxiv.org/pdf/\") or contains(., \"://arxiv.org/abs/\"))]"]' , xpath:"./*[local-name()='record']" , '(\d.*)'); +$varIdLdpg = identifierExtract('["//dc:identifier[starts-with(., \"https://doaj.org/article/\")]"]', xpath:"./*[local-name()='record']" , '(http.*)'); +$varIdUrl = identifierExtract('["//dc:relation[starts-with(., \"http\")][not(contains(., \"://doaj.org\"))][not(contains(., \"doi.org/\"))][not(contains(., \"hdl.handle.net/\"))][not(contains(., \"://nbn-resolving.de/\") or contains(., \"://nbn-resolving.org/\") or contains(., \"://resolver.obvsg.at/\") or contains(., \"://urn.fi/URN:NBN:\") or contains(., \"://urn.kb.se/resolve\"))][not(contains(., \"://arxiv.org/pdf/\") or contains(., \"://arxiv.org/abs/\"))][not(contains(., \"://localhost/\") or contains(., \"://localhost:\"))]", "//dc:relation[starts-with(., \"www\")]"]', xpath:"./*[local-name()='record']" , '((http|www).*)'); + +$varIdList = xpath:"(($varIdDoi//value, $varIdHdl//value, $varIdUrn//value, $varIdArk//value, $varIdPmid//value, $varIdPmc//value, $varIdLdpg//value, $varIdUrl//value))"; + +// dropping/cleaning wrong DOIs, as +// 2 DOIs just different in 1 ending with . (mostly, but not exclusively, prefixed with 10.5216) +// noise stemming from odd/wrong DOI statements' formats +// DOIs with 2 prefixes +// DOI statements containing first the DOI prefix and then the DOI incl. the resolver prefix +//oaf:identifier = set(xpath:"$varId//value", @identifierType = "doi";); +//oaf:identifier = set(xpath:"$varIdDoi//value", @identifierType = "doi";); + +oaf:identifier = set(xpath:"distinct-values(($varIdDoi//value[not(ends-with(., '.') and exists(index-of($varIdDoi//value, substring(., 1, string-length(.)-1))))][not(. = '10.4313/article-4')][not(lower-case(.) = ('10.30659/ijibe.2.1.171-181', '10.30659/ijibe.2.1.171', '10.26843/rencima.v8i4.149', '10.26843/rencima.v11i1.215', '10.18273/revfue.v14n2-2016002revista', '10.17061/phrp3112015', '10.21789/24222704', '10.22432/pjsr.2017.14.', '10.22432/pjsr.2017.18.02', '10.22432/pjsr.2017.18.'))][not(starts-with(., '10.1530/VAB-'))][not(starts-with(lower-case(.), '10.1155/s168761720'))][not(starts-with(., '10.15561/10.6084/') or starts-with(., '10.5935/10.19180/'))][not(starts-with(., '10.7454/jvi.v') and string-length(.) = 16)][not(starts-with(., '10.15094/0000') and string-length(.) = 16)][not(matches(., '^10\.\d*/DOI:$'))][not(starts-with(., concat(substring-before(., '/'), '/', substring-before(., '/'), '/')))][not(matches(substring-after(., '/'), '^https?://(dx.)?doi.org/.*') and starts-with(substring-after(., 'doi.org/'), substring-before(., '/')))][not(starts-with(., '10.1371/journal.') and matches(., '^10\.1371/journal\.[a-z]{4}\.\d{7}\.(eor|20050521)$'))][not(substring-before(., '/') = ('10.19183', '10.18066') and matches(., '^(10\.19183/how\.\d*\.\d*|10\.18066/revunivap\.v\d*i\d*)$'))]/lower-case(.), $varIdDoi//value[matches(substring-after(., '/'), '^https?://(dx.)?doi.org/.*') and starts-with(substring-after(., 'doi.org/'), substring-before(., '/'))]/substring-after(., 'doi.org/'), $varIdDoi//value[starts-with(., '10.1371/journal.') and matches(., '^10\.1371/journal\.[a-z]{4}\.\d{7}\.eor$')]/substring(., 1, 28), $varIdDoi//value[starts-with(., '10.15561/10.6084/') or starts-with(., '10.5935/10.19180/')]/substring-after(., '/')))", @identifierType = "doi";); + +oaf:identifier = set(xpath:"distinct-values($varIdHdl//value/normalize-space(replace(., '\?locatt=view:master', '')))", @identifierType = "handle";); +oaf:identifier = set(xpath:"$varIdUrn//value", @identifierType = "urn";); +oaf:identifier = set(xpath:"distinct-values($varIdArk//value/replace(substring-after(., '/ark:'), '^/', ''))", @identifierType = "ark";); +oaf:identifier = set(xpath:"distinct-values($varIdPmid//value/replace(., 'https?://www.ncbi.nlm.nih.gov/pmc/articles/pmid/(\d+)(/.*)?', '$1'))", @identifierType = "pmid";); +oaf:identifier = set(xpath:"distinct-values($varIdPmc//value/replace(., 'https?://(www.ncbi.nlm.nih.gov/pmc|europepmc.org)/articles/(PMC\d*)([/\?].*)?', '$2'))", @identifierType = "pmcid";); +oaf:identifier = set(xpath:"distinct-values($varIdHal//value/replace(., '/document', ''))", @identifierType = "hal";); +oaf:identifier = set(xpath:"$varIdArxv//value", @identifierType = "arxiv";); +oaf:identifier = set(xpath:"$varIdLdpg//value", @identifierType = "landingPage";); +oaf:identifier = set(xpath:"($varIdUrl//value[not(starts-with(., 'www'))], $varIdUrl//value[starts-with(., 'www')]/concat('http://', .))", @identifierType = "url";); + +oaf:datasourceprefix = xpath:"//oaf:datasourceprefix"; + +//$varJournalName = xpath:"substring-before(//dc:source, ',')"; +$varJournalTitle = xpath:"(//dc:source[contains(., ', Vol ')]/substring-before(., ', Vol '), //dc:source[contains(., ', Iss ')]/substring-before(., ', Iss '))[1]"; +$varVol = xpath:"//dc:source[contains(., ', Vol ')][matches(., ', Vol \d+')]/replace(substring-after(., ', Vol '), '^(\d+).*$', '$1')"; +$varIss = xpath:"//dc:source[contains(., ', Iss ')][matches(., ', Iss \d+')]/replace(substring-after(., ', Iss '), '^(\d+).*$', '$1')"; +$varSp = xpath:"//dc:source[contains(., ', Pp ')][matches(., ', Pp \d+-\d+')]/substring-before(substring-after(., ', Pp '), '-')"; +$varEp = xpath:"//dc:source[contains(., ', Pp ')][matches(., ', Pp \d+-\d+')]/replace(substring-after(substring-after(., ', Pp '), '-'), '^(\d+).*$', '$1')"; +$varISSN = xpath:"//dc:identifier[string-length() = 9 and matches(., '(\d{4})-(\d{4})')][1]"; +//oaf:journal = set($varJournalName, @issn = xpath:"//dc:identifier[string-length() = 9 and matches(., '^(\d{4})-(\d{4}|\d{3}X)')][1]"; , @eissn = xpath:"//dc:identifier[string-length() = 9 and matches(., '^(\d{4})-(\d{4}|\d{3}X)')][2]";); +//oaf:journal = set($varJournalName, @issn = xpath:"//dc:identifier[string-length() = 9]";); +oaf:journal = set($varJournalTitle, @issn = xpath:"//dc:identifier[string-length() = 9 and matches(., '(\d{4})-(\d{4})')][1]";, @eissn = xpath:"//dc:identifier[string-length() = 9 and matches(., '(\d{4})-(\d{4})')][2]";, @vol = xpath:"$varVol";, @iss = xpath:"$varIss";, @sp = xpath:"$varSp";, @ep = xpath:"$varEp";); + +end diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_datarepo_datacite_orig.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_cleaning_datarepo_datacite_orig.xsl similarity index 100% rename from dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_datarepo_datacite_orig.xsl rename to dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_cleaning_datarepo_datacite_orig.xsl diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid_orig.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid_orig.xsl similarity index 100% rename from dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid_orig.xsl rename to dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid_orig.xsl diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_journal.fi_orig.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_journal.fi_orig.xsl new file mode 100644 index 000000000..846e57f88 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_journal.fi_orig.xsl @@ -0,0 +1,492 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + record is not compliant, transformation is interrupted. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + landingPage + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + doi + + + + + + + + + + + + + + ORCID + + + http://orcid.org/ + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_us-pmc_orig.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_us-pmc_orig.xsl new file mode 100644 index 000000000..b3ee0c985 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/original/xslt_nlm2oaf_us-pmc_orig.xsl @@ -0,0 +1,437 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + record is not compliant, transformation is interrupted. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + eng + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + OPEN + + + + + 0001 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + doi + + + + + + pmc + + + + + + pmid + + + + + + + + + + + + + ORCID + + + http://orcid.org/ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_journal.fi.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_journal.fi.xsl new file mode 100644 index 000000000..2049a3016 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_journal.fi.xsl @@ -0,0 +1,493 @@ + + + + + + + + + + + + + + + + + + + + + + + + + record is not compliant, transformation is interrupted. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + landingPage + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + doi + + + + + + + + + + + + + + ORCID + + + http://orcid.org/ + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_us-pmc.xsl b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_us-pmc.xsl new file mode 100644 index 000000000..5c07fa1a9 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/scripts/xslt_nlm2oaf_us-pmc.xsl @@ -0,0 +1,373 @@ + + + + + + + + + + + + + + + + + + + + + + + + record is not compliant, transformation is interrupted. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + eng + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + OPEN + + + + 0001 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + doi + + + + + + pmc + + + + + + pmid + + + + + + + + + + + ORCID + + + http://orcid.org/ + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file