def transform(self, item):
xml, data = item
sub = etree.SubElement(xml, 'ListIdentifiers')
ppl = plumber.Pipeline(
HeaderPipe()
)
books = data.get('books')
items = ((sub, book) for book in books)
results = ppl.run(items)
for header in results:
pass
ppl = plumber.Pipeline(
ResumptionTokenPipe()
)
resumptionToken = ppl.run([[sub, data]])
for rt in resumptionToken:
pass
return (xml, data)
def pipeline_sci(self):
xylose_article = Article(self._article)
ppl = plumber.Pipeline(
export_sci.SetupArticlePipe(), export_sci.XMLArticlePipe(),
export_sci.XMLFrontPipe(),
export_sci.XMLJournalMetaJournalIdPipe(),
export_sci.XMLJournalMetaJournalTitleGroupPipe(),
export_sci.XMLJournalMetaISSNPipe(),
export_sci.XMLJournalMetaCollectionPipe(),
export_sci.XMLJournalMetaPublisherPipe(),
export_sci.XMLArticleMetaUniqueArticleIdPipe(),
export_sci.XMLArticleMetaArticleIdPublisherPipe(),
export_sci.XMLArticleMetaArticleIdDOIPipe(),
export_sci.XMLArticleMetaArticleCategoriesPipe(),
export_sci.XMLArticleMetaTitleGroupPipe(),
export_sci.XMLArticleMetaTranslatedTitleGroupPipe(),
export_sci.XMLArticleMetaContribGroupPipe(),
export_sci.XMLArticleMetaAffiliationPipe(),
export_sci.XMLArticleMetaDatesInfoPipe(),
export_sci.XMLArticleMetaIssueInfoPipe(),
export_sci.XMLArticleMetaElocationInfoPipe(),
export_sci.XMLArticleMetaPagesInfoPipe(),
export_sci.XMLArticleMetaPermissionPipe(),
export_sci.XMLArticleMetaURLsPipe(),
export_sci.XMLArticleMetaAbstractsPipe(),
export_sci.XMLArticleMetaKeywordsPipe(),
export_sci.XMLArticleMetaCitationsPipe(),
export_sci.XMLClosePipe())
transformed_data = ppl.run(xylose_article, rewrap=True)
return next(transformed_data)
def pipeline_pubmed(self):
xylose_article = Article(self._article, iso_format='iso 639-2')
ppl = plumber.Pipeline(export_pubmed.SetupArticleSetPipe(),
export_pubmed.XMLArticlePipe(),
export_pubmed.XMLJournalPipe(),
export_pubmed.XMLPublisherNamePipe(),
export_pubmed.XMLJournalTitlePipe(),
export_pubmed.XMLISSNPipe(),
export_pubmed.XMLVolumePipe(),
export_pubmed.XMLIssuePipe(),
export_pubmed.XMLPubDatePipe(),
export_pubmed.XMLReplacesPipe(),
export_pubmed.XMLArticleTitlePipe(),
export_pubmed.XMLFirstPagePipe(),
export_pubmed.XMLLastPagePipe(),
export_pubmed.XMLElocationIDPipe(),
export_pubmed.XMLLanguagePipe(),
export_pubmed.XMLAuthorListPipe(),
export_pubmed.XMLPublicationTypePipe(),
export_pubmed.XMLArticleIDListPipe(),
export_pubmed.XMLHistoryPipe(),
export_pubmed.XMLAbstractPipe(),
export_pubmed.XMLClosePipe())
transformed_data = ppl.run(xylose_article, rewrap=True)
return next(transformed_data)
def pipeline_rsps(self):
xylose_article = Article(self._article)
ppl = plumber.Pipeline(export_rsps.SetupArticlePipe(),
export_rsps.XMLArticlePipe(),
export_rsps.XMLFrontPipe(),
export_rsps.XMLJournalMetaJournalIdPipe(),
export_rsps.XMLJournalMetaJournalTitleGroupPipe(),
export_rsps.XMLJournalMetaISSNPipe(),
export_rsps.XMLJournalMetaPublisherPipe(),
export_rsps.XMLArticleMetaArticleIdPublisherPipe(),
export_rsps.XMLArticleMetaArticleIdDOIPipe(),
export_rsps.XMLArticleMetaArticleCategoriesPipe(),
export_rsps.XMLArticleMetaTitleGroupPipe(),
export_rsps.XMLArticleMetaTranslatedTitleGroupPipe(),
export_rsps.XMLArticleMetaContribGroupPipe(),
export_rsps.XMLArticleMetaAffiliationPipe(),
export_rsps.XMLArticleMetaGeneralInfoPipe(),
export_rsps.XMLArticleMetaHistoryPipe(),
export_rsps.XMLArticleMetaPermissionPipe(),
export_rsps.XMLArticleMetaAbstractsPipe(),
export_rsps.XMLArticleMetaKeywordsPipe(),
export_rsps.XMLArticleMetaCountsPipe(),
export_rsps.XMLBodyPipe(),
export_rsps.XMLArticleMetaCitationsPipe(),
export_rsps.XMLSubArticlePipe(),
export_rsps.XMLClosePipe())
transformed_data = ppl.run(xylose_article, rewrap=True)
return next(transformed_data)
def pipeline_doaj(self):
xylose_article = Article(self._article, iso_format='iso 639-2')
ppl = plumber.Pipeline(export_doaj.SetupArticlePipe(),
export_doaj.XMLArticlePipe(),
export_doaj.XMLJournalMetaPublisherPipe(),
export_doaj.XMLJournalMetaJournalTitlePipe(),
export_doaj.XMLJournalMetaISSNPipe(),
export_doaj.XMLArticleMetaPublicationDatePipe(),
export_doaj.XMLArticleMetaVolumePipe(),
export_doaj.XMLArticleMetaIssuePipe(),
export_doaj.XMLArticleMetaStartPagePipe(),
export_doaj.XMLArticleMetaEndPagePipe(),
export_doaj.XMLArticleMetaArticleIdDOIPipe(),
export_doaj.XMLArticleMetaIdPipe(),
export_doaj.XMLArticleMetaDocumentTypePipe(),
export_doaj.XMLArticleMetaTitlePipe(),
export_doaj.XMLArticleMetaAuthorsPipe(),
export_doaj.XMLArticleMetaAffiliationPipe(),
export_doaj.XMLArticleMetaAbstractsPipe(),
export_doaj.XMLArticleMetaFullTextUrlPipe(),
export_doaj.XMLArticleMetaKeywordsPipe(),
export_doaj.XMLClosePipe())
transformed_data = ppl.run(xylose_article, rewrap=True)
return next(transformed_data)
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 __init__(self):
self._ppl = plumber.Pipeline(
self.SetupPipe(),
self.DeprecatedHTMLTagsPipe(),
self.RemoveExcedingStyleTagsPipe(),
self.RemoveEmptyPipe(),
self.RemoveStyleAttributesPipe(),
self.BRPipe(),
self.PPipe(),
self.DivPipe(),
self.ImgPipe(),
self.LiPipe(),
self.OlPipe(),
self.UlPipe(),
self.IPipe(),
self.EmPipe(),
self.UPipe(),
self.BPipe(),
self.APipe(),
self.StrongPipe(),
self.TdCleanPipe(),
self.BlockquotePipe(),
self.HrPipe(),
self.GraphicChildrenPipe(),
self.RemoveCommentPipe(),
self.BodyAllowedTagPipe(),
self.HTMLEscapingPipe(),
self.RemovePWhichIsParentOfPPipe(),
)
def pipeline_crossref(self):
xylose_article = CustomArticle(self._article)
ppl = plumber.Pipeline(
export_crossref.SetupDoiBatchPipe(), export_crossref.XMLHeadPipe(),
export_crossref.XMLBodyPipe(), export_crossref.XMLDoiBatchIDPipe(),
export_crossref.XMLTimeStampPipe(),
export_crossref.XMLDepositorPipe(),
export_crossref.XMLRegistrantPipe(),
export_crossref.XMLJournalPipe(),
export_crossref.XMLJournalMetadataPipe(),
export_crossref.XMLJournalTitlePipe(),
export_crossref.XMLAbbreviatedJournalTitlePipe(),
export_crossref.XMLISSNPipe(),
export_crossref.XMLJournalIssuePipe(),
export_crossref.XMLPubDatePipe(), export_crossref.XMLVolumePipe(),
export_crossref.XMLIssuePipe(),
export_crossref.XMLJournalArticlePipe(),
export_crossref.XMLArticleTitlesPipe(),
export_crossref.XMLArticleTitlePipe(),
export_crossref.XMLArticleContributorsPipe(),
export_crossref.XMLArticleAbstractPipe(),
export_crossref.XMLArticlePubDatePipe(),
export_crossref.XMLPagesPipe(), export_crossref.XMLPIDPipe(),
export_crossref.XMLPermissionsPipe(),
export_crossref.XMLElocationPipe(),
export_crossref.XMLDOIDataPipe(), export_crossref.XMLDOIPipe(),
export_crossref.XMLResourcePipe(),
export_crossref.XMLCollectionPipe(),
export_crossref.XMLArticleCitationsPipe(),
export_crossref.XMLClosePipe())
transformed_data = ppl.run(xylose_article, rewrap=True)
return next(transformed_data)
def make_record(record_data, formatter):
record = etree.Element('record')
ppl = plumber.Pipeline(header, )
xmltree, _ = next(ppl.run((record, record_data), rewrap=True))
xmltree.append(formatter(record_data))
return xmltree
def __init__(self):
self._ppl = plumber.Pipeline(
self.SetupPipe(),
self.GraphicInExtLink(),
self.TableinBody(),
self.TableinP(),
self.AddPinFN(),
)
def get_meta_ppl():
ppl = plumber.Pipeline(SetupPipe(), TitlePipe(), AbbrevJournalTitlePipe(),
AbstractPipe(), JournalIDPipe(), AuthorPipe(),
AffiliationPipe(), KeywordPipe(),
DefaultLanguagePipe(), LpagePipe(), FpagePipe(),
JournalTitlePipe(), VolumePipe(), NumberPipe(),
PubDatePipe(), ISSNPipe(), PublisherNamePipe(),
SubjectPipe(), PublisherIDPipe(), TearDownPipe())
return ppl
def __init__(self):
self._ppl = plumber.Pipeline(self.SetupCitationPipe(),
self.RefIdPipe(),
self.ElementCitationPipe(),
self.ArticleTitlePipe(),
self.ThesisTitlePipe(),
self.LinkTitlePipe(), self.SourcePipe(),
self.DatePipe(), self.StartPagePipe(),
self.EndPagePipe(), self.IssuePipe(),
self.VolumePipe(), self.PersonGroupPipe(),
self.URIPipe())
def __init__(self):
self._ppl = plumber.Pipeline(self.SetupCitationPipe(),
self.CitationIdPipe(), self.ISSNPipe(),
self.JournalTitlePipe(),
self.ThesisTitlePipe(), self.AuthorPipe(),
self.VolumePipe(), self.IssuePipe(),
self.StartPagePipe(), self.DatePipe(),
self.ArticleTitlePipe(), self.ISBNPipe(),
self.SeriesTitlePipe(),
self.VolumeTitlePipe(),
self.EditionPipe())
def __str__(self):
ppl = plumber.Pipeline(
pipeline.SetupPipe(),
pipeline.ResponseDatePipe(),
pipeline.RequestPipe(),
pipeline.IdentifyNodePipe(),
pipeline.TearDownPipe()
)
results = ppl.run([self.data])
return next(results)
def transform(self, item):
xml, data = item
sub = etree.SubElement(xml, 'GetRecord')
ppl = plumber.Pipeline(
RecordPipe(),
)
results = ppl.run(data.get('books'))
record = results.next()
sub.append(record)
return (xml, data)
def __str__(self):
ppl = plumber.Pipeline(
pipeline.SetupPipe(),
pipeline.ResponseDatePipe(),
pipeline.RequestPipe(),
pipeline.MetadataFormatErrorPipe(),
pipeline.TearDownPipe()
)
results = ppl.run([self.data])
return next(results)
def transform(self, item):
xml, data = item
sub = etree.SubElement(xml, 'ListRecords')
ppl = plumber.Pipeline(
RecordPipe(),
)
results = ppl.run(data.get('books'))
for record in results:
sub.append(record)
ppl = plumber.Pipeline(
ResumptionTokenPipe()
)
resumptionToken = ppl.run([[sub, data]])
for rt in resumptionToken:
pass
return (xml, data)
def transform(self, data):
record = etree.Element('record')
ppl = plumber.Pipeline(
HeaderPipe(),
MetadataPipe()
)
results = ppl.run([(record, data)])
for result in results:
pass
return record
def transform(self, item):
xml, data = item
sub = etree.SubElement(xml, 'ListSets')
ppl = plumber.Pipeline(
SetPipe()
)
sets = data.get('books')
results = ppl.run(sets)
for _set in results:
sub.append(_set)
ppl = plumber.Pipeline(
ResumptionTokenPipe()
)
resumptionToken = ppl.run([[sub, data]])
for rt in resumptionToken:
pass
return (xml, data)
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 listidentifiers(item):
xml, data = item
listidentifiers_elem = etree.SubElement(xml, 'ListIdentifiers')
resources_data = ((listidentifiers_elem, resource)
for resource in data.get('resources', []))
add_headers_ppl = plumber.Pipeline(header)
for _ in add_headers_ppl.run(resources_data):
pass
listidentifiers_elem.append(
make_resumptiontoken(data.get('resumptionToken', '')))
return item
def __init__(self, pid, index_body=1):
self.pid = pid
self.index_body = index_body
self._ppl = plumber.Pipeline(
self.SetupPipe(super_obj=self),
self.SaveRawBodyPipe(super_obj=self),
self.DeprecatedHTMLTagsPipe(),
self.RemoveExcedingStyleTagsPipe(),
self.RemoveEmptyPipe(),
self.RemoveStyleAttributesPipe(),
self.RemoveCommentPipe(),
self.HTMLEscapingPipe(),
self.BRPipe(),
self.PPipe(),
self.DivPipe(),
self.ANamePipe(super_obj=self),
self.TablePipe(),
self.ImgPipe(),
self.LiPipe(),
self.OlPipe(),
self.UlPipe(),
self.IPipe(),
self.EmPipe(),
self.UPipe(),
self.BPipe(),
self.APipe(),
self.StrongPipe(),
self.TdCleanPipe(),
self.TableCleanPipe(),
self.BlockquotePipe(),
self.HrPipe(),
self.GraphicChildrenPipe(),
self.RemovePWhichIsParentOfPPipe(),
self.RemoveRefIdPipe(),
self.SanitizationPipe(),
)
def serialize_list_metadata_formats(data):
ppl = plumber.Pipeline(root, responsedate, request, listmetadataformats,
tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def serialize_bad_argument(data):
ppl = plumber.Pipeline(root, responsedate, request, badargument, tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def StyleCheckingPipeline():
"""Factory for style checking pipelines.
"""
return plumber.Pipeline(setup, funding_group, doctype, country_code,
teardown)
def serialize_id_does_not_exist(data):
ppl = plumber.Pipeline(root, responsedate, request, iddoesnotexist,
tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def serialize_cannot_disseminate_format(data):
ppl = plumber.Pipeline(root, responsedate, request,
cannotdisseminateformat, tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def serialize_bad_resumption_token(data):
ppl = plumber.Pipeline(root, responsedate, request, badresumptiontoken,
tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def serialize_no_records_match(data):
ppl = plumber.Pipeline(root, responsedate, request, norecordsmatch,
tobytes)
output = next(ppl.run(data, rewrap=True))
return output
def serialize_list_identifiers(data):
ppl = plumber.Pipeline(root, responsedate, request, listidentifiers,
tobytes)
output = next(ppl.run(data, rewrap=True))
return output
