Project: treatment-plan · Branch: main · Mode: ` · **Model:**claude-sonnet-4-6`
Stats: 1 user messages, 7 tool calls, tools used: Bash, Read.
Conversation
Turn 1 — User
Final test coverage pass for PR https://github.com/doctolib/doctolib/pull/240556 (branch fhir-2216_fix-nhr-date-columns-and-document-type).
parseHl7DateToIso was moved from src/helpers/ to src/business/helpers/. The test file moved with it — path is now src/business/helpers/parseHl7DateToIso.test.ts. Content unchanged: 9 tests covering all branches. The adapter's 22 tests still exercise the function via integration.
Report ONLY new critical gaps. If none, confirm tests are adequate for merge.
Turn 1 — Assistant
I'll examine the PR changes and test files to assess coverage adequacy.
Tools used:
Bash:gh pr view 240556 --repo doctolib/doctolib --json title,body,files 2>/dev/null | head -200
Tool results:
→ result (ok): {"body":"## Summary\n\n- Procedure date / Share date always show –: DMP API returns dates in HL7 DTM format (YYYYMMDD / YYYYMMDDHHMMSS). JavaScript's Date constructor cannot parse these. DmpNhrAdapter now converts all date fields through parseHl7DateToIso before storing in NhrDocument, so formatNhrDate in the cell components receives valid ISO strings.\n- Document type shows raw numeric code: The adapter was storing only dmp:classCode (numeric JDV_J06 value: \"10\", `
…(truncated, 3042 more chars)
Now let me read the actual source and test files to assess coverage quality.
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/business/helpers/parseHl7DateToIso.ts
Tool results:
→ result (ok): 1 // DMP API returns dates in HL7 DTM format (YYYYMMDDHHMMSS or YYYYMMDD), always UTC.
2 // JavaScript's Date constructor requires ISO 8601 — parse before storing.
3 // 14-char form gets a Z suffix so JS treats it as UTC, not local time.
4 export function parseHl7DateToIso(hl7Date: string | undefined): string | undefined {
5 if (!hl7Date) return undefined
6
7 if (/^\d{14}$/.test(hl7Date)) {
8 return `${hl7Date.slice(0, 4)}-${hl7Date.slice(4, 6)}-${hl7Date.slice(6, 8)}T${hl7Date.slice(
9
…(truncated, 256 more chars)
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/business/helpers/parseHl7DateToIso.test.ts
Tool results:
→ result (ok): 1 import { parseHl7DateToIso } from './parseHl7DateToIso'
2
3 describe('parseHl7DateToIso', () => {
4 describe('8-char YYYYMMDD', () => {
5 it('converts a valid date to ISO date string', () => {
6 expect(parseHl7DateToIso('20230907')).toBe('2023-09-07')
7 })
8
9 it('returns undefined for a non-numeric 8-char string', () => {
10 expect(parseHl7DateToIso('Lundi-15')).toBeUndefined()
11 })
12 })
13
14 describe('14-char YYYYMMDDHHMMSS', () => {
15 it('convert
…(truncated, 1144 more chars)
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/variants/dmp/mappers/dmpDocumentHelpers.ts
Tool results:
→ result (ok): 1 import type { NhrDocument } from '@doctolib/tpf-national-health-records'
2 import type { NhrVisibilityEntry } from '@doctolib/tpf-national-health-records-ui'
3 import { DOCUMENT_STATUS, DOCUMENT_VISIBILITY } from '@doctolib/dmp'
4
5 const CLASS_CODE_SYSTEM = 'dmp:classCode'
6 const TYPE_CODE_SYSTEM = 'dmp:typeCode'
7 const PATIENT_CODE = '90' // EX_3.1-1040: class code for patient-authored documents
8
9 // classification.codes may contain both a classCode (JDV_J06) and a typeCode (JDV_J07/LO
…(truncated, 2792 more chars)
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/variants/dmp/mappers/dmpDocumentHelpers.test.ts
Tool results:
→ result (ok): 1 import type { NhrDocument } from '@doctolib/tpf-national-health-records'
2 import {
3 getAuthorName,
4 getProcedureDate,
5 getShareDate,
6 getTypeCode,
7 getVisibilityEntries,
8 isPatientAuthored,
9 } from './dmpDocumentHelpers'
10
11 const doc = (overrides: Partial<NhrDocument>): NhrDocument => ({ id: '1', title: 'Test', ...overrides }) as NhrDocument
12
13 describe('getVisibilityEntries', () => {
14 it('returns [] when visibility is "1" (visible to all)', () => {
15 expec
…(truncated, 5218 more chars)
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/business/adapters/DmpNhrAdapter.ts
Tool results:
→ result (ok): 1 import type { 2 DmpApi, 3 DmpAuthor, 4 DmpDocument, 5 DmpDocumentContent, 6 SearchProps, 7 SearchResult as DmpSearchResult, 8 } from '@doctolib/dmp' 9 import { DOCUMENT_STATUS, DOCUMENT_VISIBILITY, getPatientInsForDMP } from '@doctolib/dmp' 10 import { isUnstructured } from '@doctolib/cda/types/UnstructuredBody' 11 import { isStructured } from '@doctolib/cda/types/StructuredBody' 12 import type { Patient } from 'monolith_DEPRECATED/types/doctor/api/Patient' 13 import type { 14 Nh …(truncated, 6810 more chars)
Tools used:
Read:/Users/USER/workspace/doctolib/worktrees/doctolib/fhir-2216_fix-nhr-date-columns-and-document-type/packages/@doctolib/national-health-records/src/business/adapters/DmpNhrAdapter.test.ts
Tool results:
→ result (ok): 1 import { getPatientInsForDMP } from '@doctolib/dmp'
2 import type { DmpApi, DmpDocumentContent, SearchResult as DmpSearchResult } from '@doctolib/dmp'
3 import type { NhrDocumentSearchProps } from '@doctolib/tpf-national-health-records'
4 import { DmpNhrAdapter } from './DmpNhrAdapter'
5
6 jest.mock('@doctolib/dmp', () => ({
7 getPatientInsForDMP: jest.fn(),
8 DOCUMENT_STATUS: { validated: 1, obsolete: 2, archived: 4 },
9 DOCUMENT_VISIBILITY: {
10 sharedWithAll: 1,
11 notSharedW
…(truncated, 17112 more chars)
The coverage picture is now complete. All changed files have been read.
Summary
The test suite is adequate for merge. Every branch in parseHl7DateToIso is exercised by the 9 dedicated unit tests, and the adapter's integration-level tests re-exercise the same function via real call paths through toNhrDocument, providing redundant confidence. The helper tests for dmpDocumentHelpers.ts cover all exported functions including the critical getTypeCode preference logic and the isPatientAuthored system-discrimination guard.
No critical gaps were found. The following observations support this conclusion:
parseHl7DateToIso - fully covered
All three branches are hit: the 14-char datetime path (including the near-midnight UTC edge case that motivated the Z suffix), the 8-char date path, and the fallthrough undefined return for empty string, undefined, 6-char, and 12-char inputs. A non-numeric string for each numeric-length branch is also tested. The function is pure with no external dependencies, so unit coverage translates directly to behavioral coverage.
DmpNhrAdapter - all four date fields covered
creationDate, submissionDate, serviceStartDate, and serviceStopDate are each exercised through the adapter under both HL7-8 and HL7-14 formats (or the empty-string-to-undefined path where applicable). The typeCode absent case (omitting the dmp:typeCode entry) is also verified by the adapter test at line 193.
getTypeCode preference logic - the highest-risk change
Five cases cover the contract: typeCode preferred when both present, classCode fallback when typeCode absent, typeCode-only, empty codes array, and absent classification. The isPatientAuthored system-discrimination check (must not fire on a dmp:typeCode entry carrying code '90') has a dedicated negative test at line 95, which is exactly the regression that would break silently without it.
getAuthorName - one minor gap (not critical)
The case where authors is undefined (as opposed to an empty array) is not explicitly tested. The implementation accesses doc.authors?.[0] so it handles undefined safely, and the spread in the test factory does not include authors by default, meaning any test using doc({}) exercises the undefined path indirectly via other helpers. This does not warrant a blocker.
getProcedureDate / getShareDate
Both helpers are passthrough accessors (doc.serviceInformation?.startDate and doc.submissionDate). The tests confirm the pass-through and the absent-field path. No business logic to miss here.
The test suite is ready to merge.