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

Jump to bottom

funders: tune search boost for acronyms #404

Merged
merged 1 commit into from
Sep 25, 2024
Merged

funders: tune search boost for acronyms #404

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
9 changes: 7 additions & 2 deletions invenio_vocabularies/contrib/funders/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
"""Vocabulary funders configuration."""

from flask import current_app
from invenio_i18n import get_locale
from invenio_i18n import lazy_gettext as _
from invenio_records_resources.services import SearchOptions
from invenio_records_resources.services.records.components import DataComponent
Expand All @@ -22,6 +23,7 @@
funder_fundref_doi_prefix = LocalProxy(
lambda: current_app.config["VOCABULARIES_FUNDER_DOI_PREFIX"]
)
localized_title = LocalProxy(lambda: f"title.{get_locale()}^20")


class FundersSearchOptions(SearchOptions):
Expand All @@ -30,9 +32,12 @@ class FundersSearchOptions(SearchOptions):
suggest_parser_cls = SuggestQueryParser.factory(
fields=[
"name^100",
"acronym.keyword^100",
"acronym^40",
localized_title,
"id^20",
"aliases^20",
"identifiers.identifier^10",
"acronym^10",
"aliases^10",
],
type="most_fields", # https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-multi-match-query.html#multi-match-types
fuzziness="AUTO", # https://www.elastic.co/guide/en/elasticsearch/reference/current/common-options.html#fuzziness
Expand Down
18 changes: 17 additions & 1 deletion invenio_vocabularies/contrib/funders/mappings/os-v1/funders/funder-v2.0.0.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,16 @@
]
}
},
"normalizer": {
"accent_normalizer": {
"type": "custom",
"char_filter": ["strip_special_chars"],
"filter": [
"lowercase",
"asciifolding"
]
}
},
"filter": {
"lowercase": {
"type": "lowercase",
Expand Down Expand Up @@ -112,7 +122,13 @@
"acronym": {
"type": "text",
"analyzer": "accent_edge_analyzer",
"search_analyzer": "accent_analyzer"
"search_analyzer": "accent_analyzer",
"fields": {
"keyword": {
"type": "keyword",
"normalizer": "accent_normalizer"
}
}
},
"status": {
"type": "keyword"
Expand Down
18 changes: 17 additions & 1 deletion invenio_vocabularies/contrib/funders/mappings/os-v2/funders/funder-v2.0.0.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,16 @@
]
}
},
"normalizer": {
"accent_normalizer": {
"type": "custom",
"char_filter": ["strip_special_chars"],
"filter": [
"lowercase",
"asciifolding"
]
}
},
"filter": {
"lowercase": {
"type": "lowercase",
Expand Down Expand Up @@ -112,7 +122,13 @@
"acronym": {
"type": "text",
"analyzer": "accent_edge_analyzer",
"search_analyzer": "accent_analyzer"
"search_analyzer": "accent_analyzer",
"fields": {
"keyword": {
"type": "keyword",
"normalizer": "accent_normalizer"
}
}
},
"status": {
"type": "keyword"
Expand Down
5 changes: 4 additions & 1 deletion tests/contrib/funders/test_funders_resource.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,9 +127,12 @@ def test_funders_suggest_sort(client, h, prefix, example_funders):
# Should show 2 results, and id=cern as first due to name
res = client.get(f"{prefix}?suggest=CERN", headers=h)
assert res.status_code == 200
assert res.json["hits"]["total"] == 2 # should be 2
assert res.json["hits"]["total"] == 3
assert res.json["hits"]["hits"][0]["name"] == "CERN"
assert res.json["hits"]["hits"][1]["name"] == "CERT"
# Matches lower, since title is boosted less
assert res.json["hits"]["hits"][2]["name"] == "OTHER"
assert res.json["hits"]["hits"][2]["title"]["en"] == "CERN"

res = client.get(f"{prefix}?suggest=N%C3%B5rthw%C3%AAst", headers=h) # Nõrthwêst
assert res.status_code == 200
Expand Down