def pipeline_to_xml(self, article):
"""
Pipeline to tranform a dictionary to XML format
:param list_dict: List of dictionary content key tronsform in a XML.
"""
ppl = plumber.Pipeline(pipeline_xml.SetupDocument(),
pipeline_xml.DocumentID(), pipeline_xml.URL(),
pipeline_xml.DOI(), pipeline_xml.Languages(),
pipeline_xml.Fulltexts(),
pipeline_xml.PublicationDate(),
pipeline_xml.Keywords(),
pipeline_xml.Collection(),
pipeline_xml.DocumentType(),
pipeline_xml.Titles(), pipeline_xml.Abstract(),
pipeline_xml.Authors(), pipeline_xml.TearDown())
xmls = ppl.run([article])
# Add root document
add = ET.Element('add')
for xml in xmls:
add.append(xml)
return ET.tostring(add, encoding="utf-8", method="xml")
def test_transform(self):
text = """<root xmlns:dc="http://www.openarchives.org/OAI/2.0/provenance">
<record>
<metadata>
<oai_dc:dc
xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/
http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:subject xml:lang="es-ES">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="es-ES">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="pt-BR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="fr-FR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="fr-FR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="fr-FR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="es-ES">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="pt-BR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
<dc:subject xml:lang="fr-FR">COVID-19 in Brazil: advantages of a socialized unified health system and preparation to contain cases</dc:subject>
</oai_dc:dc>
</metadata>
</record>
</root>
"""
xml = ET.Element("doc")
raw = ET.fromstring(text)
data = raw, xml
raw, xml = pipeline_xml.Keywords().transform(data)
self.assertEqual(3, len(xml.findall(".//field[@name='keyword_es']")))
self.assertEqual(2, len(xml.findall(".//field[@name='keyword_pt']")))
self.assertEqual(4, len(xml.findall(".//field[@name='keyword_fr']")))
def test_keywords(self):
pxml = ET.Element('doc')
data = [self._article_meta, pxml]
xmlarticle = pipeline_xml.Keywords()
raw, xml = xmlarticle.transform(data)
result = sorted([i.text for i in xml.findall('./field[@name="keyword_pt"]')])
self.assertEqual([u'Insuficiência Renal Crônica', u'Registros de Mortalidade', u'Sistemas de Informação Hospitalar', u'Terapia de Substituição Renal'], result)
def pipeline_to_xml(self, article):
"""
Pipeline to tranform a dictionary to XML format
:param list_dict: List of dictionary content key tronsform in a XML.
"""
ppl = plumber.Pipeline(pipeline_xml.SetupDocument(),
pipeline_xml.DocumentID(), pipeline_xml.DOI(),
pipeline_xml.Collection(),
pipeline_xml.DocumentType(), pipeline_xml.URL(),
pipeline_xml.Authors(), pipeline_xml.Titles(),
pipeline_xml.OriginalTitle(),
pipeline_xml.Pages(), pipeline_xml.WOKCI(),
pipeline_xml.WOKSC(),
pipeline_xml.JournalAbbrevTitle(),
pipeline_xml.Languages(),
pipeline_xml.AvailableLanguages(),
pipeline_xml.Fulltexts(),
pipeline_xml.PublicationDate(),
pipeline_xml.SciELOPublicationDate(),
pipeline_xml.SciELOProcessingDate(),
pipeline_xml.Abstract(),
pipeline_xml.AffiliationCountry(),
pipeline_xml.AffiliationInstitution(),
pipeline_xml.Sponsor(), pipeline_xml.Volume(),
pipeline_xml.SupplementVolume(),
pipeline_xml.Issue(),
pipeline_xml.SupplementIssue(),
pipeline_xml.ElocationPage(),
pipeline_xml.StartPage(),
pipeline_xml.EndPage(),
pipeline_xml.JournalTitle(),
pipeline_xml.IsCitable(),
pipeline_xml.Permission(),
pipeline_xml.Keywords(),
pipeline_xml.JournalISSNs(),
pipeline_xml.SubjectAreas(),
pipeline_xml.ReceivedCitations(),
pipeline_xml.TearDown())
xmls = ppl.run([article])
# Add root document
add = ET.Element('add')
for xml in xmls:
add.append(xml)
return ET.tostring(add, encoding="utf-8", method="xml")
def test_without_keywords(self):
pxml = ET.Element('doc')
del(self._article_meta.data['article']['v85'])
data = [self._article_meta, pxml]
xmlarticle = pipeline_xml.Keywords()
raw, xml = xmlarticle.transform(data)
result = xml.find('./field[@name="keyword_pt"]')
self.assertEqual(None, result)