Skip to content

feat(pubmed): adicionar Object[@Type=grant] (financiamento) em ObjectList #1248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Rossi-Luciano wants to merge 1 commit into
base: master
Choose a base branch
from
+166 −11
Open

feat(pubmed): adicionar Object[@Type=grant] (financiamento) em ObjectList #1248

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 46 additions & 11 deletions packtools/sps/formats/pubmed.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
article_titles,
dates,
front_articlemeta_issue,
funding_group,
journal_meta,
kwd_group,
)
Expand Down Expand Up @@ -526,6 +527,45 @@ def get_keywords(xml_tree):
return kwd_group.KwdGroup(xml_tree).extract_kwd_data_with_lang_text(subtag=False)


def get_award_groups(xml_tree):
return funding_group.FundingGroup(xml_tree).award_groups


def add_grant_objects(obj_list, xml_tree):
"""
<Object Type="grant">
<Param Name="id">RO1DK561234</Param>
<Param Name="grantor">National Institutes of Health</Param>
</Object>
"""
for award_group in get_award_groups(xml_tree):
funding_sources = [
source for source in award_group.get("funding-source") or [] if source
]
award_ids = [
award_id for award_id in award_group.get("award-id") or [] if award_id
]
grantor = "; ".join(funding_sources) or None

# acronym e country não têm fonte nos dados SciELO, ficam de fora.
for award_id in award_ids or [None]:
if not award_id and not grantor:
continue
obj = ET.Element("Object")
obj.set("Type", "grant")
if award_id:
param = ET.Element("Param")
param.set("Name", "id")
param.text = award_id
obj.append(param)
if grantor:
param = ET.Element("Param")
param.set("Name", "grantor")
param.text = grantor
obj.append(param)
obj_list.append(obj)


def xml_pubmed_object_list(xml_pubmed, xml_tree):
"""
<ObjectList>
Expand Down Expand Up @@ -553,11 +593,9 @@ def xml_pubmed_object_list(xml_pubmed, xml_tree):
</Object>
</ObjectList>
"""
kwd_list = get_keywords(xml_tree)
if not kwd_list:
return
obj_list = ET.Element("ObjectList")
for kwd in kwd_list:

for kwd in get_keywords(xml_tree):
if kwd.get("lang") == "en":
obj = ET.Element("Object")
obj.set("Type", "keyword")
Expand All @@ -566,14 +604,11 @@ def xml_pubmed_object_list(xml_pubmed, xml_tree):
param.text = kwd.get("text")
obj.append(param)
obj_list.append(obj)
xml_pubmed.append(obj_list)

# TODO
# The Object tag includes the Type attribute, which may include only one of the following values
# for each identifier.
# Grant, Comment, Dataset, Erratum, Originalreport, Partialretraction, Patientsummary,
# Reprint, Republished, Retraction, Update.
# There is no example of using this value in the files.
add_grant_objects(obj_list, xml_tree)

if len(obj_list):
xml_pubmed.append(obj_list)


def xml_pubmed_title_reference_list(xml_pubmed, xml_tree):
Expand Down
120 changes: 120 additions & 0 deletions tests/sps/formats/test_pubmed.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1288,6 +1288,126 @@ def test_xml_pubmed_object_list_keyword(self):

self.assertEqual(obtained, expected)

def test_xml_pubmed_object_list_grant(self):
expected = (
'<Article>'
'<ObjectList>'
'<Object Type="grant">'
'<Param Name="id">04/08142-0</Param>'
'<Param Name="grantor">Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)</Param>'
'</Object>'
'<Object Type="grant">'
'<Param Name="id">05/07183-0</Param>'
'<Param Name="grantor">FAPESP; CAPES</Param>'
'</Object>'
'</ObjectList>'
'</Article>'
)
xml_pubmed = ET.fromstring(
'<Article/>'
)
xml_tree = ET.fromstring(
'<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
'xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" '
'dtd-version="1.1" specific-use="sps-1.9" xml:lang="en">'
'<front>'
'<article-meta>'
'<funding-group>'
'<award-group>'
'<funding-source>Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)</funding-source>'
'<award-id>04/08142-0</award-id>'
'</award-group>'
'<award-group>'
'<funding-source>FAPESP</funding-source>'
'<funding-source>CAPES</funding-source>'
'<award-id>05/07183-0</award-id>'
'</award-group>'
'</funding-group>'
'</article-meta>'
'</front>'
'</article>'
)

xml_pubmed_object_list(xml_pubmed, xml_tree)

obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")

self.assertEqual(obtained, expected)

def test_xml_pubmed_object_list_keyword_and_grant(self):
expected = (
'<Article>'
'<ObjectList>'
'<Object Type="keyword">'
'<Param Name="value">Arteries Dissection</Param>'
'</Object>'
'<Object Type="grant">'
'<Param Name="id">04/08142-0</Param>'
'<Param Name="grantor">FAPESP</Param>'
'</Object>'
'</ObjectList>'
'</Article>'
)
xml_pubmed = ET.fromstring(
'<Article/>'
)
xml_tree = ET.fromstring(
'<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
'xmlns:xlink="http://www.w3.org/1999/xlink" article-type="letter" dtd-version="1.1" '
'specific-use="sps-1.9" xml:lang="pt">'
'<front>'
'<article-meta>'
'<kwd-group xml:lang="pt">'
'<kwd>Dissecção das Artérias</kwd>'
'</kwd-group>'
'<funding-group>'
'<award-group>'
'<funding-source>FAPESP</funding-source>'
'<award-id>04/08142-0</award-id>'
'</award-group>'
'</funding-group>'
'</article-meta>'
'</front>'
'<sub-article article-type="translation" id="TRen" xml:lang="en">'
'<front-stub>'
'<kwd-group xml:lang="en">'
'<kwd>Arteries Dissection</kwd>'
'</kwd-group>'
'</front-stub>'
'</sub-article>'
'</article>'
)

xml_pubmed_object_list(xml_pubmed, xml_tree)

obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")

self.assertEqual(obtained, expected)

def test_xml_pubmed_object_list_without_keyword_or_grant(self):
expected = (
'<Article/>'
)
xml_pubmed = ET.fromstring(
'<Article/>'
)
xml_tree = ET.fromstring(
'<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
'xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" '
'dtd-version="1.1" specific-use="sps-1.9" xml:lang="en">'
'<front>'
'<article-meta>'
'</article-meta>'
'</front>'
'</article>'
)

xml_pubmed_object_list(xml_pubmed, xml_tree)

obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")

self.assertEqual(obtained, expected)

def test_xml_pubmed_title_reference_list(self):
expected = (
'<Article>'
Expand Down