0cececd7-a2e7-4a75-a26c-21df764ad54e

Committed 24 Aug 2025 10:29PM UTC coverage: 41.169% (-2.5%) from 43.704%

Build # 0cececd7-a2e7-4a75-a26c-21df764ad54e

Build Type

push

circleci

Committed by

mpasternak

Commit Message

Merge branch 'release/v202508.1206'

Run Details

1 of 1 new or added line in 1 file covered. (100.0%)

2674 existing lines in 124 files now uncovered.

16057 of 39003 relevant lines covered (41.17%)

0.76 hits per line

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

24.14

src/crossref_bpp/utils.py

from __future__ import annotations

import json
import textwrap

from django.db import models

from django.contrib.postgres.search import TrigramSimilarity


def json_format_with_wrap(item: [] | {} | str | None, width: int = 70) -> str:
    """Formatuje 'ładnie' dane JSON, w sytuacji, gdyby jakas linia
    przekraczała szerokośc ``width``, zawija.
    """
    s = json.dumps(item, indent=2).split("\n")
    news = []
    for elem in s:
        if len(elem) > width:
            elem = textwrap.fill(elem, width=width)
        news.append(elem)
    return "\n".join(news)


def perform_trigram_search(
    queryset,
    trigram_db_field,
    trigram_db_value,
    max_number_records=5,
    minimum_acceptable_similarity=0.6,
    db_trigram_target="podobienstwo",
    similarity_step_down=0.05,
    similarity_step_up=0.01,
    max_steps=20,
) -> list[models.Model] | None:
    """Performs a TrigramSimilarity search, starting from similarity value of
    1.0, desceding every ``step`` as long as the number of records is below ``max_number_records``

    :param queryset: Django queryset, can be anything.
    :param trigram_db_field: trigram database field, can be Lower('db_column') etc,
    :param trigram_db_value: value you're looking for in trigram_db_field, will be used
    to compare similarity.
    """

    kwargs_annotate = {
        db_trigram_target: TrigramSimilarity(trigram_db_field, trigram_db_value)
    }

    current_similarity = 1.0
    current_step = 0
    while (
        current_similarity > minimum_acceptable_similarity or current_step >= max_steps
    ):
        current_step += 1
        kwargs_filter = {db_trigram_target + "__gte": current_similarity}
        my_queryset = queryset.annotate(**kwargs_annotate).filter(**kwargs_filter)

        cnt = my_queryset[: max_number_records + 1].count()
        if cnt == max_number_records + 1:
            # Za dużo rekordów. Zwiększ nieznacznie pożądane podobieństwo i szukaj dalej.
            current_similarity += similarity_step_up
            continue

        if cnt == 0:
            # Za mało rekordów. Zmniejsz poszukiwane prawdopodobieństwo:
            current_similarity -= similarity_step_down
            continue

        return my_queryset.order_by(f"-{db_trigram_target}")

1	from __future__ import annotations	2✔
2
3	import json	2✔
4	import textwrap	2✔
5
6	from django.db import models	2✔
7
8	from django.contrib.postgres.search import TrigramSimilarity	2✔
9
10
11	def json_format_with_wrap(item: [] \| {} \| str \| None, width: int = 70) -> str:	2✔
12	"""Formatuje 'ładnie' dane JSON, w sytuacji, gdyby jakas linia
13	przekraczała szerokośc ``width``, zawija.
14	"""
UNCOV 15	s = json.dumps(item, indent=2).split("\n")	×
UNCOV 16	news = []	×
UNCOV 17	for elem in s:	×
UNCOV 18	if len(elem) > width:	×
UNCOV 19	elem = textwrap.fill(elem, width=width)	×
UNCOV 20	news.append(elem)	×
UNCOV 21	return "\n".join(news)	×
22
23
24	def perform_trigram_search(	2✔
25	queryset,
26	trigram_db_field,
27	trigram_db_value,
28	max_number_records=5,
29	minimum_acceptable_similarity=0.6,
30	db_trigram_target="podobienstwo",
31	similarity_step_down=0.05,
32	similarity_step_up=0.01,
33	max_steps=20,
34	) -> list[models.Model] \| None:
35	"""Performs a TrigramSimilarity search, starting from similarity value of
36	1.0, desceding every ``step`` as long as the number of records is below ``max_number_records``
37
38	:param queryset: Django queryset, can be anything.
39	:param trigram_db_field: trigram database field, can be Lower('db_column') etc,
40	:param trigram_db_value: value you're looking for in trigram_db_field, will be used
41	to compare similarity.
42	"""
43
UNCOV 44	kwargs_annotate = {	×
45	db_trigram_target: TrigramSimilarity(trigram_db_field, trigram_db_value)
46	}
47
UNCOV 48	current_similarity = 1.0	×
UNCOV 49	current_step = 0	×
UNCOV 50	while (	×
51	current_similarity > minimum_acceptable_similarity or current_step >= max_steps
52	):
UNCOV 53	current_step += 1	×
UNCOV 54	kwargs_filter = {db_trigram_target + "__gte": current_similarity}	×
UNCOV 55	my_queryset = queryset.annotate(kwargs_annotate).filter(kwargs_filter)	×
56
UNCOV 57	cnt = my_queryset[: max_number_records + 1].count()	×
UNCOV 58	if cnt == max_number_records + 1:	×
59	# Za dużo rekordów. Zwiększ nieznacznie pożądane podobieństwo i szukaj dalej.
60	current_similarity += similarity_step_up	×
61	continue	×
62
UNCOV 63	if cnt == 0:	×
64	# Za mało rekordów. Zmniejsz poszukiwane prawdopodobieństwo:
UNCOV 65	current_similarity -= similarity_step_down	×
UNCOV 66	continue	×
67
68	return my_queryset.order_by(f"-{db_trigram_target}")	×

iplweb / bpp / 0cececd7-a2e7-4a75-a26c-21df764ad54e

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