ec27228a8e
Em dashes (—) and en dashes (–) had spread across comments, docs, tests, and a few UI strings, reading as AI-generated boilerplate rather than house style. Replaced each with punctuation matching its context: colon for explanatory clauses, comma for asides, plain hyphen for numeric/legal ranges (e.g. "21-23§"), "to"/"till" for date ranges, parentheses for paired-dash asides. messages/en.json and messages/sv.json were fixed by hand together to keep sv/en in sync. Left untouched where the dash is the functional subject rather than decorative punctuation: date-range-parser.ts's separator regex, charset-repair.ts's CP1252 byte-mapping table (and its test), the SIE encoding mojibake docs, generic-csv.ts's minus-sign normalizer, the agent system-prompt files that already instruct against em dashes, and a golden iXBRL test fixture compared byte-for-byte. Also fixes two bugs surfaced along the way: an off-by-one in ApiKeysPanel's scope-label split (a leftover from an earlier partial pass), and a charset-repair test that had lost the literal en-dash it exists to verify. Regenerated the agent atom seed migration (skills:generate) since 27 SKILL.md files changed. Added a CLAUDE.md rule against em/en dashes, with an explicit carve-out for the functional-dash cases above. Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
93 lines
2.6 KiB
TypeScript
93 lines
2.6 KiB
TypeScript
'use client'
|
|
|
|
import { useEffect, useState } from 'react'
|
|
|
|
// Polls GET /api/documents/:id/extraction-status until the AI extraction
|
|
// pipeline completes, fails, or times out. Returns the derived status the
|
|
// upload UI binds to.
|
|
//
|
|
// "Disabled" semantics: if the document-extraction extension isn't enabled
|
|
// (the column stays NULL forever), we don't know server-side. Instead we
|
|
// stop polling after EXTRACTION_TIMEOUT_MS and bubble status='disabled' so
|
|
// the UI can quietly fall back ("Uppladdat" without an AI hint): no scary
|
|
// error for a feature the customer didn't pay for.
|
|
//
|
|
// Reasonable timeout: typical extraction takes 2-8s on Sonnet via Bedrock.
|
|
// 30s is generous and keeps the UX responsive on flaky links.
|
|
|
|
const POLL_INTERVAL_MS = 1500
|
|
const EXTRACTION_TIMEOUT_MS = 30_000
|
|
|
|
export type ExtractionStatus =
|
|
| 'idle'
|
|
| 'running'
|
|
| 'succeeded'
|
|
| 'failed'
|
|
| 'unsupported'
|
|
| 'disabled'
|
|
|
|
interface State {
|
|
status: ExtractionStatus
|
|
// Hint to consumers: how long we've been polling. Lets the UI swap the
|
|
// copy after a few seconds ("Läser fakturan…" → "Tar lite längre än
|
|
// vanligt…") without re-rendering.
|
|
elapsedMs: number
|
|
}
|
|
|
|
export function useDocumentExtraction(documentId: string | null | undefined): State {
|
|
const [state, setState] = useState<State>({ status: 'idle', elapsedMs: 0 })
|
|
|
|
useEffect(() => {
|
|
if (!documentId) {
|
|
setState({ status: 'idle', elapsedMs: 0 })
|
|
return
|
|
}
|
|
|
|
let cancelled = false
|
|
const startedAt = Date.now()
|
|
setState({ status: 'running', elapsedMs: 0 })
|
|
|
|
async function tick(): Promise<void> {
|
|
if (cancelled) return
|
|
const elapsedMs = Date.now() - startedAt
|
|
|
|
if (elapsedMs > EXTRACTION_TIMEOUT_MS) {
|
|
setState({ status: 'disabled', elapsedMs })
|
|
return
|
|
}
|
|
|
|
try {
|
|
const res = await fetch(`/api/documents/${documentId}/extraction-status`)
|
|
if (cancelled) return
|
|
if (res.ok) {
|
|
const json = (await res.json()) as {
|
|
data: { status: ExtractionStatus }
|
|
}
|
|
const status = json.data.status
|
|
if (status !== 'running') {
|
|
setState({ status, elapsedMs })
|
|
return
|
|
}
|
|
setState({ status: 'running', elapsedMs })
|
|
}
|
|
// Non-ok responses fall through to retry; transient 5xx shouldn't
|
|
// collapse the UI to "failed".
|
|
} catch {
|
|
// Network blip: keep polling.
|
|
}
|
|
|
|
setTimeout(() => {
|
|
if (!cancelled) void tick()
|
|
}, POLL_INTERVAL_MS)
|
|
}
|
|
|
|
void tick()
|
|
|
|
return () => {
|
|
cancelled = true
|
|
}
|
|
}, [documentId])
|
|
|
|
return state
|
|
}
|