def get_document_sps_package(current_version):
"""
Dada a versão atual do documento registrado no Kernel, retorna um objeto de
SPS_Package
Args:
current_version (str): a versão atual do documento registrado no Kernel
Returns:
SPS_Package
Raises:
GetSPSPackageFromDocManifestException
"""
response = requests.get(current_version["data"])
try:
xml_str = response.text.encode("utf-8")
xml_tree = etree.fromstring(xml_str)
return SPS_Package(xml_tree, '')
except (
AttributeError,
etree.XMLSyntaxError,
etree.Error,
) as e:
raise GetSPSPackageFromDocManifestException(
"Unable to get SPS Package of %s: %s" %
(current_version["data"], e)
)
def get_sps_package(self, issue):
xml_text = f"""
<article><article-meta>
<issue>{issue}</issue>
</article-meta></article>
"""
xmltree = etree.fromstring(xml_text)
return SPS_Package(xmltree, "sps_package")
def is_document_to_delete(zipfile, sps_xml_file):
parser = etree.XMLParser(remove_blank_text=True, no_network=True)
try:
metadata = SPS_Package(etree.XML(zipfile.read(sps_xml_file), parser),
sps_xml_file)
except (etree.XMLSyntaxError, TypeError, KeyError) as exc:
raise DocumentToDeleteException(str(exc)) from None
else:
return metadata.is_document_deletion, metadata.scielo_pid_v3
def get_xml_data(xml_content, xml_package_name):
"""
- Obter scielo ID
- Obter infos de periódico e fascículo
- Obter nomes dos arquivos ativos digitais
- Obter nomes dos arquivos PDF
- Obter idiomas (original e traduções)
"""
parser = etree.XMLParser(remove_blank_text=True, no_network=True)
try:
metadata = SPS_Package(etree.XML(xml_content, parser),
xml_package_name)
except (etree.XMLSyntaxError, TypeError) as exc:
raise PutXMLInObjectStoreException(
'Could not get xml data from "{}" : {}'.format(
xml_package_name, str(exc))) from None
else:
pdfs = [{
"lang": metadata.original_language,
"filename": "{}.pdf".format(xml_package_name),
"mimetype": "application/pdf",
}]
for lang in metadata.translation_languages:
pdfs.append({
"lang": lang,
"filename": "{}-{}.pdf".format(xml_package_name, lang),
"mimetype": "application/pdf",
})
_xml_data = {
"scielo_id":
metadata.scielo_id,
"issn":
metadata.issn,
"year":
metadata.year,
"order":
metadata.order,
"xml_package_name":
xml_package_name,
"assets": [{
"asset_id": asset_name
} for asset_name in metadata.assets_names],
"pdfs":
pdfs,
}
for attr in ["volume", "number", "supplement"]:
if getattr(metadata, attr) is not None:
_xml_data[attr] = getattr(metadata, attr)
return _xml_data
def _get_related_articles(xml):
"""
Obtém a lista de documentos relacionados do XML e atualiza os
documentos dessa realação.
Tag no XML que representa essa relação:
<related-article ext-link-type="doi" id="ra1"
related-article-type="corrected-article"
xlink:href="10.1590/S0103-50532006000200015"/>
"""
try:
etree_xml = et.XML(xml)
except ValueError as ex:
logging.error("Erro ao tentar analisar(parser) do XML, erro: %s",
ex)
else:
sps_package = SPS_Package(etree_xml)
for related_dict in sps_package.related_articles:
_update_related_articles(article, related_dict)