def testSruTermDrilldown(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [
{'fieldname': 'field0', 'terms': [{'term': 'value0_0', 'count': 14}]},
{'fieldname': 'field1', 'terms': [{'term': 'value1_0', 'count': 13}, {'term': 'value1_1', 'count': 11}]},
{'fieldname': 'field2', 'terms': [{'term': 'value2_0', 'count': 3}, {'term': 'value2_1', 'count': 2}, {'term': 'value2_2', 'count': 1}]}
]
response = ''.join(compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={})))
self.assertEqualsWS(DRILLDOWN_HEADER + """<dd:term-drilldown><dd:navigator name="field0">
<dd:item count="14">value0_0</dd:item>
</dd:navigator>
<dd:navigator name="field1">
<dd:item count="13">value1_0</dd:item>
<dd:item count="11">value1_1</dd:item>
</dd:navigator>
<dd:navigator name="field2">
<dd:item count="3">value2_0</dd:item>
<dd:item count="2">value2_1</dd:item>
<dd:item count="1">value2_2</dd:item>
</dd:navigator></dd:term-drilldown></dd:drilldown>""", response)
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testEchoedExtraRequestDataWithJsonFormat(self):
component = SruTermDrilldown()
result = "".join(
list(
component.echoedExtraRequestData(sruArguments={
'x-term-drilldown': ['field0/field1,field2', 'field3'],
'version':
'1.1',
'x-drilldown-format': ['json']
},
version='1.1')))
self.assertEqualsWS(_DRILLDOWN_HEADER % _DRILLDOWN_XSD_2013 + """
<dd:request>
<dd:x-term-drilldown>field0/field1</dd:x-term-drilldown>
<dd:x-term-drilldown>field2</dd:x-term-drilldown>
<dd:x-term-drilldown>field3</dd:x-term-drilldown>
<dd:x-drilldown-format>json</dd:x-drilldown-format>
</dd:request>""" +\
DRILLDOWN_FOOTER, result)
xsdFilename = self._getXsdFilename(result)
assertValid(result, join(schemasPath, xsdFilename))
with open(join(schemasPath, xsdFilename)) as fp:
assertValid(fp.read(), join(schemasPath, 'XMLSchema.xsd'))
def testEchoedExtraRequestData(self):
component = SruTermDrilldown()
result = "".join(list(component.echoedExtraRequestData(sruArguments={'x-term-drilldown': ['field0,field1'], 'version': '1.1'}, version='1.1')))
self.assertEqualsWS(DRILLDOWN_HEADER \
+ """<dd:term-drilldown>field0,field1</dd:term-drilldown>"""\
+ DRILLDOWN_FOOTER, result)
def testSruTermDrilldown(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [{
'fieldname': 'field0',
'terms': [{
'term': 'value0_0',
'count': 14
}]
}, {
'fieldname':
'field1',
'terms': [{
'term': 'value1_0',
'count': 13
}, {
'term': 'value1_1',
'count': 11
}]
}, {
'fieldname':
'field2',
'terms': [{
'term': 'value2_0',
'count': 3
}, {
'term': 'value2_1',
'count': 2
}, {
'term': 'value2_2',
'count': 1
}]
}]
response = ''.join(
compose(
sruTermDrilldown.extraResponseData(drilldownData,
sruArguments={})))
self.assertEqualsWS(
DRILLDOWN_HEADER +
"""<dd:term-drilldown><dd:navigator name="field0">
<dd:item count="14">value0_0</dd:item>
</dd:navigator>
<dd:navigator name="field1">
<dd:item count="13">value1_0</dd:item>
<dd:item count="11">value1_1</dd:item>
</dd:navigator>
<dd:navigator name="field2">
<dd:item count="3">value2_0</dd:item>
<dd:item count="2">value2_1</dd:item>
<dd:item count="1">value2_2</dd:item>
</dd:navigator></dd:term-drilldown></dd:drilldown>""", response)
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testEchoedExtraRequestDataWithEmptyTermDrilldownFormat(self):
component = SruTermDrilldown(defaultFormat=FORMAT_XML)
result = "".join(
list(
component.echoedExtraRequestData(sruArguments={
'x-term-drilldown': [''],
'version': '1.1'
},
version='1.1')))
self.assertEqualsWS("", result)
def testEchoedExtraRequestData(self):
component = SruTermDrilldown()
result = "".join(
list(
component.echoedExtraRequestData(sruArguments={
'x-term-drilldown': ['field0,field1'],
'version':
'1.1'
},
version='1.1')))
self.assertEqualsWS(DRILLDOWN_HEADER \
+ """<dd:term-drilldown>field0,field1</dd:term-drilldown>"""\
+ DRILLDOWN_FOOTER, result)
def testDrilldownNoResults(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [
{'fieldname': 'field0', 'terms': []},
]
composedGenerator = compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={}))
result = "".join(composedGenerator)
expected = DRILLDOWN_HEADER + """
<dd:term-drilldown>
<dd:navigator name="field0"/>
</dd:term-drilldown>
""" + DRILLDOWN_FOOTER
self.assertEqualsWS(expected, result)
def testWrongFormat(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [
{
'fieldname': 'field0',
'terms': [
{
'term': 'value0',
'count': 1,
}
]
}
]
response = parse(StringIO(''.join(compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={'x-drilldown-format':'text'})))))
self.assertEqualsWS("Expected x-drilldown-format to be one of: ['xml', 'json']", xpathFirst(response, '//drilldown:term-drilldown/diag:diagnostic/diag:message/text()'))
def testEchoedExtraRequestDataWithJsonFormat(self):
component = SruTermDrilldown()
result = "".join(list(component.echoedExtraRequestData(sruArguments={'x-term-drilldown': ['field0/field1,field2','field3'], 'version': '1.1', 'x-drilldown-format': ['json']}, version='1.1')))
self.assertEqualsWS(_DRILLDOWN_HEADER % _DRILLDOWN_XSD_2013 + """
<dd:request>
<dd:x-term-drilldown>field0/field1</dd:x-term-drilldown>
<dd:x-term-drilldown>field2</dd:x-term-drilldown>
<dd:x-term-drilldown>field3</dd:x-term-drilldown>
<dd:x-drilldown-format>json</dd:x-drilldown-format>
</dd:request>""" +\
DRILLDOWN_FOOTER, result)
xsdFilename = self._getXsdFilename(result)
assertValid(result, join(schemasPath, xsdFilename))
assertValid(open(join(schemasPath, xsdFilename)).read(), join(schemasPath, 'XMLSchema.xsd'))
def testDefaultFormat(self):
self.assertRaises(ValueError, lambda: SruTermDrilldown(defaultFormat='text'))
sruTermDrilldown = SruTermDrilldown(defaultFormat='json')
drilldownData = [
{
'fieldname': 'field0',
'terms': [
{
'term': 'value0',
'count': 1,
}
]
}
]
response = parse(StringIO(''.join(compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={})))))
self.assertEquals(drilldownData, loads(xpathFirst(response, '//drilldown:term-drilldown/drilldown:json/text()')))
def testDrilldownNoResults(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [
{
'fieldname': 'field0',
'terms': []
},
]
composedGenerator = compose(
sruTermDrilldown.extraResponseData(drilldownData, sruArguments={}))
result = "".join(composedGenerator)
expected = DRILLDOWN_HEADER + """
<dd:term-drilldown>
<dd:navigator name="field0"/>
</dd:term-drilldown>
""" + DRILLDOWN_FOOTER
self.assertEqualsWS(expected, result)
def testSruTermDrilldownWithSubTerms(self):
sruTermDrilldown = SruTermDrilldown(defaultFormat=FORMAT_XML)
drilldownData = [{
'fieldname':
'field0',
'terms': [{
'term':
'value0',
'count':
1,
'subterms': [{
'term': 'value0_0',
'count': 10,
}, {
'term': 'value0_1',
'count': 20
}]
}, {
'term': 'value1',
'count': 2
}]
}]
response = ''.join(
compose(
sruTermDrilldown.extraResponseData(drilldownData,
sruArguments={})))
self.assertEqualsWS(
_DRILLDOWN_HEADER % _DRILLDOWN_XSD_2013 +
"""<dd:term-drilldown><dd:navigator name="field0">
<dd:item count="1" value="value0">
<dd:navigator name="subterms">
<dd:item count="10" value="value0_0"/>
<dd:item count="20" value="value0_1"/>
</dd:navigator>
</dd:item>
<dd:item count="2" value="value1"/>
</dd:navigator></dd:term-drilldown></dd:drilldown>""", response)
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testSruTermDrilldownWithSubTerms(self):
sruTermDrilldown = SruTermDrilldown(defaultFormat=FORMAT_XML)
drilldownData = [
{
'fieldname': 'field0',
'terms': [
{
'term': 'value0',
'count': 1,
'subterms': [
{
'term': 'value0_0',
'count': 10,
},
{
'term': 'value0_1',
'count': 20
}
]
},
{
'term': 'value1',
'count': 2
}
]
}
]
response = ''.join(compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={})))
self.assertEqualsWS(_DRILLDOWN_HEADER % _DRILLDOWN_XSD_2013 + """<dd:term-drilldown><dd:navigator name="field0">
<dd:item count="1" value="value0">
<dd:navigator name="subterms">
<dd:item count="10" value="value0_0"/>
<dd:item count="20" value="value0_1"/>
</dd:navigator>
</dd:item>
<dd:item count="2" value="value1"/>
</dd:navigator></dd:term-drilldown></dd:drilldown>""", response)
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testSruTermDrilldownWithPivotsInJson(self):
sruTermDrilldown = SruTermDrilldown(defaultFormat=FORMAT_JSON)
drilldownData = [{
'fieldname':
'field0',
'terms': [{
'term': 'value0',
'count': 1,
'pivot': {
'fieldname':
'field1',
'terms': [{
'term': 'value0_0',
'count': 10,
}, {
'term': 'value0 & 1',
'count': 20
}]
}
}, {
'term': 'value1',
'count': 2
}]
}]
response = ''.join(
compose(
sruTermDrilldown.extraResponseData(
drilldownData,
sruArguments={'x-drilldown-format': ['json']})))
self.assertEqual(
drilldownData,
loads(
xpathFirst(
XML(response),
'//drilldown:term-drilldown/drilldown:json/text()')))
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testWrongFormat(self):
sruTermDrilldown = SruTermDrilldown()
drilldownData = [{
'fieldname': 'field0',
'terms': [{
'term': 'value0',
'count': 1,
}]
}]
response = parse(
StringIO(''.join(
compose(
sruTermDrilldown.extraResponseData(
drilldownData,
sruArguments={'x-drilldown-format': 'text'})))))
self.assertEqualsWS(
"Expected x-drilldown-format to be one of: ['xml', 'json']",
xpathFirst(
response,
'//drilldown:term-drilldown/diag:diagnostic/diag:message/text()'
))
def testSruTermDrilldownWithPivotsInJson(self):
sruTermDrilldown = SruTermDrilldown(defaultFormat=FORMAT_JSON)
drilldownData = [
{
'fieldname': 'field0',
'terms': [
{
'term': 'value0',
'count': 1,
'pivot': {
'fieldname': 'field1',
'terms': [
{
'term': 'value0_0',
'count': 10,
},
{
'term': 'value0 & 1',
'count': 20
}
]
}
},
{
'term': 'value1',
'count': 2
}
]
}
]
response = ''.join(compose(sruTermDrilldown.extraResponseData(drilldownData, sruArguments={'x-drilldown-format': ['json']})))
self.assertEquals(drilldownData, loads(xpathFirst(XML(response), '//drilldown:term-drilldown/drilldown:json/text()')))
xsdFilename = self._getXsdFilename(response)
assertValid(response, join(schemasPath, xsdFilename))
def testDefaultFormat(self):
self.assertRaises(ValueError,
lambda: SruTermDrilldown(defaultFormat='text'))
sruTermDrilldown = SruTermDrilldown(defaultFormat='json')
drilldownData = [{
'fieldname': 'field0',
'terms': [{
'term': 'value0',
'count': 1,
}]
}]
response = parse(
StringIO(''.join(
compose(
sruTermDrilldown.extraResponseData(drilldownData,
sruArguments={})))))
self.assertEqual(
drilldownData,
loads(
xpathFirst(
response,
'//drilldown:term-drilldown/drilldown:json/text()')))
def main(reactor, port, statePath, lucenePort, **ignored):
######## START Lucene Integration ###############################################################
defaultLuceneSettings = LuceneSettings(
commitTimeout=30,
readonly=True,)
http11Request = be(
(HttpRequest1_1(),
(SocketPool(reactor=reactor, unusedTimeout=5, limits=dict(totalSize=100, destinationSize=10)),),
)
)
luceneIndex = luceneAndReaderConfig(defaultLuceneSettings.clone(readonly=True), http11Request, lucenePort)
luceneRoHelix = be(
(AdapterToLuceneQuery(
defaultCore=DEFAULT_CORE,
coreConverters={
DEFAULT_CORE: QueryExpressionToLuceneQueryDict(UNQUALIFIED_TERM_FIELDS, luceneSettings=luceneIndex.settings),
}
),
(MultiLucene(host='127.0.0.1', port=lucenePort, defaultCore=DEFAULT_CORE),
(luceneIndex,),
(http11Request,),
)
)
)
######## END Lucene Integration ###############################################################
fieldnameRewrites = {}
def fieldnameRewrite(name):
return fieldnameRewrites.get(name, name)
def drilldownFieldnamesTranslate(fieldname):
untokenizedName = untokenizedFieldname(fieldname)
if untokenizedName in untokenizedFieldnames:
fieldname = untokenizedName
return fieldnameRewrite(fieldname)
convertToComposedQuery = ConvertToComposedQuery(
resultsFrom=DEFAULT_CORE,
matches=[],
drilldownFieldnamesTranslate=drilldownFieldnamesTranslate
)
strategie = Md5HashDistributeStrategy()
storage = StorageComponent(join(statePath, 'store'), strategy=strategie, partsRemovedOnDelete=[HEADER_PARTNAME, META_PARTNAME, METADATA_PARTNAME, OAI_DC_PARTNAME, LONG_PARTNAME, SHORT_PARTNAME])
# Wat doet dit?
cqlClauseConverters = [
RenameFieldForExact(
untokenizedFields=untokenizedFieldnames,
untokenizedPrefix=UNTOKENIZED_PREFIX,
).filterAndModifier(),
SearchTermFilterAndModifier(
shouldModifyFieldValue=lambda *args: True,
fieldnameModifier=fieldnameRewrite
).filterAndModifier(),
]
executeQueryHelix = \
(FilterMessages(allowed=['executeQuery']),
(CqlMultiSearchClauseConversion(cqlClauseConverters, fromKwarg='query'),
(DrilldownQueries(),
(convertToComposedQuery,
(luceneRoHelix,),
)
)
)
)
return \
(Observable(),
(ObservableHttpServer(reactor, port, compressResponse=True),
(BasicHttpHandler(),
(PathFilter(['/sru']),
(SruParser(
host='sru.narcis.nl',
port=80,
defaultRecordSchema='knaw_short',
defaultRecordPacking='xml'),
(SruLimitStartRecord(limitBeyond=4000),
(SruHandler(
includeQueryTimes=False,
extraXParameters=[],
enableCollectLog=False), #2017-03-24T12:00:33Z 127.0.0.1 3.5K 0.019s - /sru OF (TRUE): 2017-03-24T11:58:53Z 127.0.0.1 2.3K 0.004s 1hits /sru maximumRecords=10&operation=searchRetrieve&query=untokenized.dd_year+exact+%221993%22&recordPacking=xml&recordSchema=knaw_short&startRecord=1&version=1.2
(SruTermDrilldown(),),
executeQueryHelix,
(StorageAdapter(),
(storage,)
)
)
)
)
),
(PathFilter('/rss'),
(Rss( supportedLanguages = ['nl','en'], # defaults to first, if requested language is not available or supplied.
title = {'nl':'NARCIS', 'en':'NARCIS'},
description = {'nl':'NARCIS: De toegang tot de Nederlandse wetenschapsinformatie', 'en':'NARCIS: The gateway to Dutch scientific information'},
link = {'nl':'http://www.narcis.nl/?Language=nl', 'en':'http://www.narcis.nl/?Language=en'},
maximumRecords = 20),
executeQueryHelix,
(RssItem(
nsMap=NAMESPACEMAP,
title = ('knaw_short', {'nl':'//short:metadata/short:titleInfo[not (@xml:lang)]/short:title/text()', 'en':'//short:metadata/short:titleInfo[@xml:lang="en"]/short:title/text()'}),
description = ('knaw_short', {'nl':'//short:abstract[not (@xml:lang)]/text()', 'en':'//short:abstract[@xml:lang="en"]/text()'}),
pubdate = ('knaw_short', '//short:dateIssued/short:parsed/text()'),
linkTemplate = 'http://www.narcis.nl/%(wcpcollection)s/RecordID/%(oai_identifier)s/Language/%(language)s',
wcpcollection = ('meta', '//*[local-name() = "collection"]/text()'),
oai_identifier = ('meta', '//meta:record/meta:id/text()'),
language = ('Dummy: Language is auto provided by the calling RSS component, but needs to be present to serve the linkTemplate.')
),
(StorageAdapter(),
(storage,)
)
)
)
)
)
)
)
def testEchoedExtraRequestDataWithEmptyTermDrilldownFormat(self):
component = SruTermDrilldown(defaultFormat=FORMAT_XML)
result = "".join(list(component.echoedExtraRequestData(sruArguments={'x-term-drilldown': [''], 'version': '1.1'}, version='1.1')))
self.assertEqualsWS("", result)
def main(reactor,
port,
statePath,
lucenePort,
gatewayPort,
quickCommit=False,
**ignored):
######## START Lucene Integration ###############################################################
defaultLuceneSettings = LuceneSettings(
commitTimeout=30,
readonly=True,
)
http11Request = be((
HttpRequest1_1(),
(SocketPool(reactor=reactor,
unusedTimeout=5,
limits=dict(totalSize=100, destinationSize=10)), ),
))
luceneIndex = luceneAndReaderConfig(
defaultLuceneSettings.clone(readonly=True), http11Request, lucenePort)
luceneRoHelix = be(
(AdapterToLuceneQuery(defaultCore=DEFAULT_CORE,
coreConverters={
DEFAULT_CORE:
QueryExpressionToLuceneQueryDict(
UNQUALIFIED_TERM_FIELDS,
luceneSettings=luceneIndex.settings),
}), (
MultiLucene(host='localhost',
port=lucenePort,
defaultCore=DEFAULT_CORE),
(luceneIndex, ),
(http11Request, ),
)))
######## END Lucene Integration ###############################################################
fieldnameRewrites = {
# UNTOKENIZED_PREFIX+'genre': UNTOKENIZED_PREFIX+'dc:genre',
}
def fieldnameRewrite(name):
return fieldnameRewrites.get(name, name)
def drilldownFieldnamesTranslate(fieldname):
untokenizedName = untokenizedFieldname(fieldname)
if untokenizedName in untokenizedFieldnames:
fieldname = untokenizedName
return fieldnameRewrite(fieldname)
convertToComposedQuery = ConvertToComposedQuery(
resultsFrom=DEFAULT_CORE,
matches=[],
drilldownFieldnamesTranslate=drilldownFieldnamesTranslate)
strategie = Md5HashDistributeStrategy()
storage = StorageComponent(join(statePath, 'store'),
strategy=strategie,
partsRemovedOnDelete=[
HEADER_PARTNAME, META_PARTNAME,
METADATA_PARTNAME, OAI_DC_PARTNAME,
LONG_PARTNAME, SHORT_PARTNAME,
OPENAIRE_PARTNAME
])
oaiJazz = OaiJazz(join(statePath, 'oai'))
oaiJazz.updateMetadataFormat(
OAI_DC_PARTNAME, "http://www.openarchives.org/OAI/2.0/oai_dc.xsd",
"http://purl.org/dc/elements/1.1/")
oai_oa_cerifJazz = OaiJazz(join(statePath, 'oai_cerif'))
oai_oa_cerifJazz.updateMetadataFormat(
OPENAIRE_PARTNAME,
"https://www.openaire.eu/schema/cris/current/openaire-cerif-profile.xsd",
"https://www.openaire.eu/cerif-profile/1.1/")
# All of the following OAI-PMH sets shall be recognized by the CRIS, even if not all of them are populated.
oai_oa_cerifJazz.updateSet("openaire_cris_projects",
"OpenAIRE_CRIS_projects")
oai_oa_cerifJazz.updateSet("openaire_cris_orgunits",
"OpenAIRE_CRIS_orgunits")
oai_oa_cerifJazz.updateSet("openaire_cris_persons",
"OpenAIRE_CRIS_persons")
oai_oa_cerifJazz.updateSet("openaire_cris_patents",
"OpenAIRE_CRIS_patents")
oai_oa_cerifJazz.updateSet("openaire_cris_products",
"OpenAIRE_CRIS_products")
oai_oa_cerifJazz.updateSet("openaire_cris_publications",
"OpenAIRE_CRIS_publications")
oai_oa_cerifJazz.updateSet("openaire_cris_funding",
"OpenAIRE_CRIS_funding")
oai_oa_cerifJazz.updateSet("openaire_cris_events", "OpenAIRE_CRIS_events")
oai_oa_cerifJazz.updateSet("openaire_cris_equipments",
"OpenAIRE_CRIS_equipments")
cqlClauseConverters = [
RenameFieldForExact(
untokenizedFields=untokenizedFieldnames,
untokenizedPrefix=UNTOKENIZED_PREFIX,
).filterAndModifier(),
SearchTermFilterAndModifier(
shouldModifyFieldValue=lambda *args: True,
fieldnameModifier=fieldnameRewrite).filterAndModifier(),
]
periodicGateWayDownload = PeriodicDownload(
reactor,
host='localhost',
port=gatewayPort,
schedule=Schedule(
period=1 if quickCommit else 10
), # WST: Interval in seconds before sending a new request to the GATEWAY in case of an error while processing batch records.(default=1). IntegrationTests need 1 second! Otherwise tests will fail!
name='api',
autoStart=True)
oaiDownload = OaiDownloadProcessor(path='/oaix',
metadataPrefix=NORMALISED_DOC_NAME,
workingDirectory=join(
statePath, 'harvesterstate',
'gateway'),
userAgentAddition='ApiServer',
xWait=True,
name='api',
autoCommit=False)
executeQueryHelix = \
(FilterMessages(allowed=['executeQuery']),
(CqlMultiSearchClauseConversion(cqlClauseConverters, fromKwarg='query'),
(DrilldownQueries(),
(convertToComposedQuery,
(luceneRoHelix,),
)
)
)
)
return \
(Observable(),
createDownloadHelix(reactor, periodicGateWayDownload, oaiDownload, storage, oaiJazz, oai_oa_cerifJazz),
(ObservableHttpServer(reactor, port, compressResponse=True),
(BasicHttpHandler(),
(PathFilter(["/oai"]),
(OaiPmh(repositoryName="NARCIS OAI-pmh", adminEmail="*****@*****.**", externalUrl="http://oai.narcis.nl"),
(oaiJazz,),
(StorageAdapter(),
(storage,)
),
(OaiBranding(
url="http://www.narcis.nl/images/logos/logo-knaw-house.gif",
link="http://oai.narcis.nl",
title="Narcis - The gateway to scholarly information in The Netherlands"),
),
(OaiProvenance(
nsMap=NAMESPACEMAP,
baseURL=('meta', '//meta:repository/meta:baseurl/text()'),
harvestDate=('meta', '//meta:record/meta:harvestdate/text()'),
metadataNamespace=('meta', '//meta:record/meta:metadataNamespace/text()'),
identifier=('header','//oai:identifier/text()'),
datestamp=('header', '//oai:datestamp/text()')
),
(storage,)
)
)
),
(PathFilter(["/cerif"]),
(OaiPmhDans(repositoryName="OpenAIRE CERIF", adminEmail="*****@*****.**", repositoryIdentifier="services.nod.dans.knaw.nl", externalUrl="http://services.nod.dans.knaw.nl"), #TODO: pathFilter should resemble proxy path
(oai_oa_cerifJazz,),
(StorageAdapter(),
(storage,)
),
(OaiOpenAIREDescription(
serviceid='organisation:ORG1242054',
acronym='services.nod.dans.knaw.nl',
name='NARCIS',
description='Compliant with the OpenAIRE Guidelines for CRIS Managers v.1.1.',
website='https://www.narcis.nl',
baseurl='http://services.nod.dans.knaw.nl/oa-cerif',
subjectheading='',
orgunitid='organisation:ORG1242054',
owneracronym='DANS'),
),
# (OaiBranding(
# url="http://www.narcis.nl/images/logos/logo-knaw-house.gif",
# link="http://oai.narcis.nl",
# title="Narcis - The gateway to scholarly information in The Netherlands"),
# ),
(OaiProvenance(
nsMap=NAMESPACEMAP,
baseURL=('meta', '//meta:repository/meta:baseurl/text()'),
harvestDate=('meta', '//meta:record/meta:harvestdate/text()'),
metadataNamespace=('meta', '//meta:record/meta:metadataNamespace/text()'),
identifier=('header','//oai:identifier/text()'),
datestamp=('header', '//oai:datestamp/text()')
),
(storage,)
)
)
),
(PathFilter(['/sru']),
(SruParser(
host='sru.narcis.nl',
port=80,
defaultRecordSchema='knaw_short',
defaultRecordPacking='xml'),
(SruLimitStartRecord(limitBeyond=4000),
(SruHandler(
includeQueryTimes=False,
extraXParameters=[],
enableCollectLog=False),
(SruTermDrilldown(),),
executeQueryHelix,
(StorageAdapter(),
(storage,)
)
)
)
)
),
(PathFilter('/rss'),
(Rss( supportedLanguages = ['nl','en'], # defaults to first, if requested language is not available or supplied.
title = {'nl':'NARCIS', 'en':'NARCIS'},
description = {'nl':'NARCIS: De toegang tot de Nederlandse wetenschapsinformatie', 'en':'NARCIS: The gateway to Dutch scientific information'},
link = {'nl':'http://www.narcis.nl/?Language=nl', 'en':'http://www.narcis.nl/?Language=en'},
maximumRecords = 20),
executeQueryHelix,
(RssItem(
nsMap=NAMESPACEMAP,
title = ('knaw_short', {'nl':'//short:metadata/short:titleInfo[not (@xml:lang)]/short:title/text()', 'en':'//short:metadata/short:titleInfo[@xml:lang="en"]/short:title/text()'}),
description = ('knaw_short', {'nl':'//short:abstract[not (@xml:lang)]/text()', 'en':'//short:abstract[@xml:lang="en"]/text()'}),
pubdate = ('knaw_short', '//short:dateIssued/short:parsed/text()'),
linkTemplate = 'http://www.narcis.nl/%(wcpcollection)s/RecordID/%(oai_identifier)s/Language/%(language)s',
wcpcollection = ('meta', '//*[local-name() = "collection"]/text()'),
oai_identifier = ('meta', '//meta:record/meta:id/text()'),
language = ('Dummy: Language is auto provided by the calling RSS component, but needs to be present to serve the linkTemplate.')
),
(StorageAdapter(),
(storage,)
)
)
)
)
)
)
)
