17425918180

Committed 03 Sep 2025 07:11AM UTC coverage: 95.796% (-0.6%) from 96.378%

Build # 17425918180

Build Type

push

github

Committed by

PascalRepond

Commit Message

translations: extract messages

Co-Authored-by: Pascal Repond <pascal.repond@rero.ch>

Run Details

7816 of 8159 relevant lines covered (95.8%)

0.96 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

94.29

/sonar/affiliations/affiliation_resolver.py

# Swiss Open Access Repository
# Copyright (C) 2021 RERO
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

"""Affiliations resolver."""

import csv

from fuzzywuzzy import fuzz
from werkzeug.utils import cached_property

CSV_FILE = "./data/affiliations.csv"


class AffiliationResolver:
    """Affiliation resolver."""

    @cached_property
    def affiliations(self):
        """List of affiliations retrieved from a dedicated file.

        :returns: List of affliations
        """
        affiliations = []

        with open(CSV_FILE) as file:
            reader = csv.reader(file, delimiter="\t")
            for row in reader:
                affiliation = []
                for index, value in enumerate(row):
                    if index > 0 and value:
                        affiliation.append(value)

                if affiliation:
                    affiliations.append(affiliation)

        return affiliations

    def resolve(self, searched_affiliation):
        """Resolve affiliations from given parameter.

        :param searched_affiliation: Affiliation to match.
        :returns: String of matching affiliation.
        """
        if not searched_affiliation:
            return None

        collected_affiliations = []
        for affiliations in self.affiliations:
            # the first string in the row is the standard form, to be stored
            standard_form = affiliations[0]
            for affiliation in affiliations:
                score = fuzz.partial_ratio(searched_affiliation, affiliation)
                if score > 92 and standard_form not in collected_affiliations:
                    # handle special case UZH / ZHdK
                    # TODO: solve this special case by converting the CSV file to JSON
                    # using rejected forms https://github.com/rero/sonar/issues/824
                    if (
                        affiliation.lower() == "zurich university"
                        and "zurich university of the arts" in searched_affiliation.lower()
                    ):
                        continue
                    # handle special case CERN/Lucerne
                    if affiliation.lower() == "cern" and "lucerne" in searched_affiliation.lower():
                        continue
                    # handle special case Freiburg im Breisgau
                    if "university of freiburg" in searched_affiliation.lower():
                        break

                    collected_affiliations.append(standard_form)
        return collected_affiliations

1	# Swiss Open Access Repository
2	# Copyright (C) 2021 RERO
3	#
4	# This program is free software: you can redistribute it and/or modify
5	# it under the terms of the GNU Affero General Public License as published by
6	# the Free Software Foundation, version 3 of the License.
7	#
8	# This program is distributed in the hope that it will be useful,
9	# but WITHOUT ANY WARRANTY; without even the implied warranty of
10	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11	# GNU Affero General Public License for more details.
12	#
13	# You should have received a copy of the GNU Affero General Public License
14	# along with this program. If not, see <http://www.gnu.org/licenses/>.
15
16	"""Affiliations resolver."""
17
18	import csv	1✔
19
20	from fuzzywuzzy import fuzz	1✔
21	from werkzeug.utils import cached_property	1✔
22
23	CSV_FILE = "./data/affiliations.csv"	1✔
24
25
26	class AffiliationResolver:	1✔
27	"""Affiliation resolver."""
28
29	@cached_property	1✔
30	def affiliations(self):	1✔
31	"""List of affiliations retrieved from a dedicated file.
32
33	:returns: List of affliations
34	"""
35	affiliations = []	1✔
36
37	with open(CSV_FILE) as file:	1✔
38	reader = csv.reader(file, delimiter="\t")	1✔
39	for row in reader:	1✔
40	affiliation = []	1✔
41	for index, value in enumerate(row):	1✔
42	if index > 0 and value:	1✔
43	affiliation.append(value)	1✔
44
45	if affiliation:	1✔
46	affiliations.append(affiliation)	1✔
47
48	return affiliations	1✔
49
50	def resolve(self, searched_affiliation):	1✔
51	"""Resolve affiliations from given parameter.
52
53	:param searched_affiliation: Affiliation to match.
54	:returns: String of matching affiliation.
55	"""
56	if not searched_affiliation:	1✔
57	return None	1✔
58
59	collected_affiliations = []	1✔
60	for affiliations in self.affiliations:	1✔
61	# the first string in the row is the standard form, to be stored
62	standard_form = affiliations[0]	1✔
63	for affiliation in affiliations:	1✔
64	score = fuzz.partial_ratio(searched_affiliation, affiliation)	1✔
65	if score > 92 and standard_form not in collected_affiliations:	1✔
66	# handle special case UZH / ZHdK
67	# TODO: solve this special case by converting the CSV file to JSON
68	# using rejected forms https://github.com/rero/sonar/issues/824
69	if (	1✔
70	affiliation.lower() == "zurich university"
71	and "zurich university of the arts" in searched_affiliation.lower()
72	):
73	continue	×
74	# handle special case CERN/Lucerne
75	if affiliation.lower() == "cern" and "lucerne" in searched_affiliation.lower():	1✔
76	continue	×
77	# handle special case Freiburg im Breisgau
78	if "university of freiburg" in searched_affiliation.lower():	1✔
79	break	1✔
80
81	collected_affiliations.append(standard_form)	1✔
82	return collected_affiliations	1✔

rero / sonar / 17425918180

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous