14ba6690-9c33-4ca2-ab73-fa1fd8aa6215

Committed 21 May 2026 08:58AM UTC coverage: 9.992% (+3.0%) from 7.009%

Build # 14ba6690-9c33-4ca2-ab73-fa1fd8aa6215

Build Type

Pull #497

circleci

Committed by

marc-gavanier

Commit Message

feat: improve structure fusion scoring and review export

Significantly reduces the manual review burden by detecting more
true duplicates automatically and avoiding false positives.

Scoring improvements (detect-duplicate-structures, generate-structures-action-plan):
- Treat clusters of type 'mixte' like 'doublon_certain' with per-pair
  scoring (instead of bulk verification_manuelle), uncovering hundreds
  of auto/probable fusions previously hidden in mixed clusters.
- Boost address score to 1.0 when one normalized address is contained
  in the other (e.g. "Lupino" vs "LUPINO PARVIS NOTRE DAME VICTOIRE").
- Add address abbreviations: VC (voie communale), RT (route), ZA, ZI, CH.
- Redistribute geo weight when coords are unavailable, OR when address
  strongly indicates the same place (>=0.85): prevents penalizing
  structures with missing or erroneous coords.
- Normalize "commune de/du", "mairie de/du", "ville de/du" to a single
  "ville" canonical token so variants match.
- Detect "service keywords" (EPN, médiathèque, CCAS, France services,
  MJC, etc.): when one name has such a keyword and the other does not,
  they are distinct entities even with shared SIRET/address. Disables
  the address-contained heuristic and keeps geo in the score.

Sync resilience (findOrCreateStructure):
- After strict siret+codeInsee miss, fall back to siret-only with
  normalized contained-name match. This catches Dataspace structures
  whose codeInsee diverges from the coop's, without merging an EPN
  with its parent town hall (asymmetric-service-keyword guard).

Review output:
- generate-structures-action-plan: structures-fusion-review.csv now
  uses cluster-grouped format (CIBLE + sources + empty line between
  clusters, sorted by ascending score), matching the existing format
  Tim uses for his manual reviews.
- export-duplicate-sirets: cluster-grouped CSV (empty line between
  SIRETs) and exclude empty-string siret. Enrich each row with
  nom_api, adresse_api, corre... (continued)

Pull Request Pull Request #497: feat: improve structure fusion scoring and review export

Coverage Stats

688 of 10876 branches covered (6.33%)

Branch coverage included in aggregate %.

26 of 150 new or added lines in 4 files covered. (17.33%)

911 existing lines in 95 files now uncovered.

2111 of 17137 relevant lines covered (12.32%)

1.94 hits per line

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

0.0

/apps/web/src/worksheet/buildWorksheetHelpers.ts

1	import type { SessionUser } from '@app/web/auth/sessionUser'
2	import type {
3	ActivitesFiltersLabels,
4	FilterType,
5	} from '@app/web/features/activites/use-cases/list/components/generateActivitesFiltersLabels'
6	import { addTitleRow } from '@app/web/libs/worksheet/addTitleRow'
7	import type { Worksheet } from 'exceljs'
8
UNCOV 9	const onlyType = (type: string) => (filter: { type: string }) =>	×
UNCOV 10	filter.type === type	×
11
UNCOV 12	const toLabel = ({ label }: { label: string }) => label	×
13
14	export const addFilters =
UNCOV 15	(worksheet: Worksheet) =>	×
UNCOV 16	(	×
17	filters: ActivitesFiltersLabels,
18	{
19	mediateurScope,
20	excludeFilters = [],	×
21	}: {
22	mediateurScope: null \| Pick<SessionUser, 'firstName' \| 'lastName'>
23	excludeFilters?: FilterType[]
24	},
25	) => {
UNCOV 26	addTitleRow(worksheet)('Filtres')	×
27
UNCOV 28	return worksheet.addRows(	×
29	[
30	!excludeFilters.includes('periode')	×
31	? [
32	'Période',
UNCOV 33	filters.find((filter) => filter.type === 'periode')?.label ?? '-',	×
34	]
35	: undefined,
36	!excludeFilters.includes('source')	×
37	? [
38	'Source',
UNCOV 39	filters.find((filter) => filter.type === 'source')?.label ?? '-',	×
40	]
41	: undefined,
42	!excludeFilters.includes('lieux')	×
43	? [
44	'Lieux d’accompagnement',
45	filters	×
46	.filter(onlyType('lieux'))
UNCOV 47	.map(({ label }) => label)	×
48	.join(', ') \|\| '-',
49	]
50	: undefined,
51	!excludeFilters.includes('communes')	×
52	? [
53	'Communes',
54	filters.filter(onlyType('communes')).map(toLabel).join(', ') \|\|	×
55	'-',
56	]
57	: undefined,
58	!excludeFilters.includes('departements')	×
59	? [
60	'Départements',
61	filters	×
62	.filter(onlyType('departements'))
63	.map(toLabel)
64	.join(', ') \|\| '-',
65	]
66	: undefined,
67	!excludeFilters.includes('types')	×
68	? [
69	'Type d’accompagnement',
70	filters.filter(onlyType('types')).map(toLabel).join(', ') \|\| '-',	×
71	]
72	: undefined,
73	!excludeFilters.includes('conseiller_numerique')	×
74	? [
75	'Rôle',
UNCOV 76	filters.find((filter) => filter.type === 'conseiller_numerique')	×
77	?.label ?? '-',
78	]
79	: undefined,
80	!excludeFilters.includes('thematiqueNonAdministratives')	×
81	? [
82	'Thématiques non administratives',
83	filters	×
84	.filter(onlyType('thematiqueNonAdministratives'))
85	.map(toLabel)
86	.join(', ') \|\| '-',
87	]
88	: undefined,
89	!excludeFilters.includes('thematiqueAdministratives')	×
90	? [
91	'Thématiques administratives',
92	filters	×
93	.filter(onlyType('thematiqueAdministratives'))
94	.map(toLabel)
95	.join(', ') \|\| '-',
96	]
97	: undefined,
98	!excludeFilters.includes('tags')	×
99	? [
100	'Tags',
101	filters.filter(onlyType('tags')).map(toLabel).join(', ') \|\| '-',	×
102	]
103	: undefined,
104	!excludeFilters.includes('beneficiaires') &&	×
105	filters.filter(onlyType('beneficiaires')).length > 0
106	? [
107	'Bénéficiaires',
108	filters	×
109	.filter(onlyType('beneficiaires'))
110	.map(toLabel)
111	.join(', ') \|\| '-',
112	]
113	: undefined,
114	!excludeFilters.includes('mediateurs') &&	×
115	filters.filter(onlyType('mediateurs')).length > 0
116	? [
117	'Médiateurs',
118	filters.filter(onlyType('mediateurs')).map(toLabel).join(', ') \|\|	×
119	'-',
120	]
121	: undefined,
122	mediateurScope	×
123	? [
124	'Médiateur',
125	`${mediateurScope.firstName} ${mediateurScope.lastName}`,
126	]
127	: undefined,
128	[],
129	].filter(Boolean),
130	)
131	}

inclusion-numerique / coop-mediation-numerique / 14ba6690-9c33-4ca2-ab73-fa1fd8aa6215

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