Skip to content
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

update section cv mapping to item[subject] [BOR-28] #97

Merged
merged 2 commits into from
Nov 27, 2024
Merged

update section cv mapping to item[subject] [BOR-28] #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5c2b600
udpate section cv mapping to item[subject] [BOR-28]
devketanpro Nov 27, 2024
66562f8
refactore code
devketanpro Nov 27, 2024
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
23 changes: 14 additions & 9 deletions server/borsen/io/feed_parsers/ritzau.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,30 +24,35 @@ class RitzauFeedParser(BaseRitzauFeedParser):
def __init__(self):
super().__init__()
self.default_mapping.update(
{"anpa_category": {"xpath": "sectionID/text()", "filter": self.section_category_filter}}
{
"subject": {
"xpath": "sectionID/text()",
"filter": self.section_category_filter,
}
}
)

def do_mapping(self, item, item_xml, setting_param_name=None, namespaces=None):
item = super().do_mapping(item, item_xml, setting_param_name, namespaces)

# Add Default Category:
sections_cv_items = self.get_cv_items("sections")
default_section = [section for section in sections_cv_items if section["qcode"] == "generelt"]
categories_cv_items = self.get_cv_items("categories")
default_section = [section for section in categories_cv_items if str(section["qcode"]) == "generelt"]

if default_section:
item["anpa_category"].append(default_section[0])
item.setdefault("anpa_category", []).append(default_section[0])

return item

def section_category_filter(self, category):
voc_categories = self.get_cv_items("sections")
if voc_categories:
categories_cv = {str(i["ritzau_section_id"]): i for i in voc_categories if "ritzau_section_id" in i}
cv_sections_items = self.get_cv_items("sections")
if cv_sections_items:
section_cv = {str(i["ritzau_section_id"]): i for i in cv_sections_items if "ritzau_section_id" in i}
else:
categories_cv = {}
section_cv = {}

populated_categories = []
match = categories_cv.get(category)
match = section_cv.get(str(category))
if match:
populated_categories.append(match)
return populated_categories
Expand Down
15 changes: 11 additions & 4 deletions server/tests/io/feed_parsers/ritzau_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,9 @@ class BaseRitzauTestCase(TestCase):
def setUp(self):
super().setUp()
voc_file = os.path.join(
os.path.abspath(os.path.dirname(os.path.dirname(borsen.__file__))), "tests/io/fixtures", "vocabularies.json"
os.path.abspath(os.path.dirname(os.path.dirname(borsen.__file__))),
"tests/io/fixtures",
"vocabularies.json",
)
AppPopulateCommand().run(voc_file)
for key in dir(settings):
Expand Down Expand Up @@ -57,7 +59,7 @@ def test_can_parse(self):
def test_content(self):
item = self.item
self.assertEqual(
item["anpa_category"],
item["subject"],
[
{
"name": "Sandbox",
Expand All @@ -66,14 +68,19 @@ def test_content(self):
"translations": {"name": {"da": "Sandbox"}},
"ritzau_section_id": "4",
"scheme": "sections",
},
}
],
)
self.assertEqual(
item["anpa_category"],
[
{
"name": "Generelt",
"qcode": "generelt",
"subject": None,
"translations": {"name": {"da": "Generelt"}},
"ritzau_section_id": "",
"scheme": "sections",
"scheme": "categories",
},
],
)
Expand Down
28 changes: 14 additions & 14 deletions server/tests/io/fixtures/vocabularies.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
"is_active": true,
"name": "foo",
"qcode": "f1",
"ritzau_section_id": 1,
"ritzau_section_id": "1",
"subject": "",
"translations": {
"name": {
Expand All @@ -24,14 +24,26 @@
"is_active": true,
"name": "bar",
"qcode": "f2",
"ritzau_section_id": 2,
"ritzau_section_id": "2",
"subject": "",
"translations": {
"name": {
"fr": "article-fr",
"es": "article-es"
}
}
},
{
"is_active":true,
"name":"Generelt",
"qcode":"generelt",
"subject":null,
"translations":{
"name":{
"da":"Generelt"
}
},
"ritzau_section_id":""
}
],
"schema": {
Expand Down Expand Up @@ -110,18 +122,6 @@
}
},
"ritzau_section_id": ""
},
{
"is_active":true,
"name":"Generelt",
"qcode":"generelt",
"subject":null,
"translations":{
"name":{
"da":"Generelt"
}
},
"ritzau_section_id":""
}
],
"schema":{
Expand Down
Loading