evidence-source/workplans/ESRC-WP-0002-html-markdown-representations.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

1.8 KiB

id type title domain repo status owner topic_slug created updated spec_refs state_hub_workstream_id
ESRC-WP-0002 workplan HTML and Markdown source representations infotech evidence-source finished codex citation_evidence_mvp 2026-07-08 2026-07-09
README.md
docs/ADR-0001-extraction-boundary.md
docs/ADR-0003-html-markdown-representation.md
../citation-engine/src/shared/document.ts
12f0b386-0df1-50d9-8cf7-4829d5257382

ESRC-WP-0002 — HTML and Markdown source representations

The PDF slice (ESRC-WP-0001) established the ingest boundary and contract shape. This workplan extends ingest to HTML and Markdown sources, producing the same { document, representation } pair over engine-owned contracts.

Decisions (ADR-0003)

  • HTML maps to representationType: "html-dom"; Markdown to "markdown-rendered".
  • Pageless formats omit pageMap; offsetMap is a single synthetic page-1 range covering [0, canonicalText.length).
  • Inline fixtures owned by this repo (no PII); PDF corpus rules unchanged.

Sketch

id: ESRC-WP-0002-T01
status: done
priority: medium
state_hub_task_id: "f875c025-2c08-56d7-bbde-60e0643a7b9c"

Define the HTML/MD representation contract with citation-engine; agree representationType and any offset/page semantics for pageless formats.

id: ESRC-WP-0002-T02
status: done
priority: medium
state_hub_task_id: "e7936d67-188d-50f3-8dc8-684c9f03fb4a"

Implement ingestHtml / ingestMarkdown in src/html/ and src/markdown/, reusing fingerprintBytes and the canonical-text normalizer.

id: ESRC-WP-0002-T03
status: done
priority: medium
state_hub_task_id: "18fcce8a-92f6-5e52-b613-ffa52f18bc71"

Add fixture-driven contract tests mirroring the PDF suite; decide fixture ownership per ADR-0002.