evidence-source/workplans/ESRC-WP-0003-metadata-enrichment.md
codex 24aad6ec6a
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
fix(workplans): adopt ADR-007 derived identifiers for unregistered records
These workplans exist only in the retired local hub. Their random pre-ADR-007
identifiers are refused by C-06 as stale references, so they cannot be
registered. Deriving from the canonical record id takes no identity from
anything: central does not hold them and the old ids die with the cache.

Records central already holds were deliberately left untouched.

Refs CUST-WP-0068-T06

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-25 20:10:10 +02:00

53 lines
No EOL
1.4 KiB
Markdown

---
id: ESRC-WP-0003
type: workplan
title: "Document metadata enrichment beyond pass-through options"
domain: infotech
repo: evidence-source
status: finished
owner: codex
topic_slug: citation_evidence_mvp
created: "2026-07-08"
updated: "2026-07-09"
spec_refs:
- README.md
- src/pdf/ingest.ts
- src/pdf/metadata.ts
state_hub_workstream_id: "16444f5e-93f2-5a7f-a2f1-92284315d041"
---
# ESRC-WP-0003 — Metadata enrichment
Today `ingestPdf` only passes through caller-supplied `title`/`uri`/`metadata`.
This workplan extracts intrinsic document metadata (PDF info dictionary,
embedded XMP, page-derived signals like author/creation date/title) and folds
it into the `Document` record without breaking the pure-over-bytes contract.
## Sketch
```task
id: ESRC-WP-0003-T01
status: done
priority: low
state_hub_task_id: "01187f2c-f6fa-549e-91ad-a0acc46bcd36"
```
Enumerate available PDF metadata sources (info dict, XMP) via PDF.js and decide
precedence vs. caller-supplied options (caller wins).
```task
id: ESRC-WP-0003-T02
status: done
priority: low
state_hub_task_id: "95176499-3ae7-586d-bce4-a96c075632ab"
```
Implement extraction into a normalized metadata shape; keep it optional so
minimal-metadata PDFs still ingest cleanly.
```task
id: ESRC-WP-0003-T03
status: done
priority: low
state_hub_task_id: "83fa3027-61f7-5bb9-95ce-ffbe58c90ebd"
```
Contract tests over the fixture corpus asserting extracted vs. overridden
metadata precedence.