Align public site with wayseer00 text canon

.github/workflows/pull-request.yml

@@ -28,9 +28,9 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Verify canon authority
-        run: node -e "const c=require('./src/_data/generated/canon.json'); if(c.source.repository!=='wayseer00/wayseer.github.io'||c.source.path!=='canon/the_interdependent_way.md') process.exit(1)"
+        run: node -e "const c=require('./src/_data/generated/canon.json'); if(c.source.repository!=='wayseer00/main'||c.source.path!=='canon/INTERDEPENDENT_WAY.txt') process.exit(1)"
       - name: Verify canon unit evidence
-        run: node -e "const c=require('./src/_data/generated/canon.json'); if(!c.source.contentSha256||c.source.contentSha256.length!==64||!c.units.length||c.units.some(u=>!u.id||!u.hash)) process.exit(1)"
+        run: node -e "const c=require('./src/_data/generated/canon.json'); if(!c.source.contentSha256||c.source.contentSha256.length!==64||(!c.source.fallback&&(!c.source.commit||!c.source.blob))||!c.units.length||c.units.some(u=>!u.id||!u.hash)) process.exit(1)"
       - name: Verify repository route coverage
         run: node -e "const r=require('./src/_data/generated/repos.json'); if(r.publicRepoCount!==r.generatedRouteCount||new Set(r.repositories.map(x=>x.slug)).size!==r.repositories.length) process.exit(1)"
       - name: Verify recovery inputs

README.md

@@ -4,7 +4,7 @@ This repository builds `interdependentway.org`: a static-first, progressively la
 
 ## What is authoritative
 
-The canonical identity remains `wayseer00/wayseer.github.io:canon/the_interdependent_way.md`. The repository copy at `canon/the_interdependent_way.md` is a recovery mirror. Build output records whether the remote source or recovery mirror supplied the current snapshot, together with SHA-256 provenance.
+The canonical text lives in `wayseer00/main:canon/INTERDEPENDENT_WAY.txt`, and nowhere in this repository supersedes it. The repository copy at `canon/the_interdependent_way.md` is a recovery mirror only. Build output records whether the remote source or recovery mirror supplied the current snapshot, together with SHA-256 provenance; successful remote retrieval also records the resolved source commit and blob SHA.
 
 ## Architecture
 

docs/architecture.md

@@ -4,8 +4,8 @@ The production site is generated into `_site` by Eleventy. Pages are complete HT
 
 ## Data paths
 
-- `scripts/fetch-canon.mjs` retrieves the Wayseer canonical alias `wayseer00/wayseer.github.io:canon/the_interdependent_way.md`. The transferred repository copy at `canon/the_interdependent_way.md` is recovery-only and is recorded as a fallback when used.
-- `scripts/parse-canon.mjs` generates units, line ranges, note text, relationships, and SHA-256 digests.
+- `scripts/fetch-canon.mjs` retrieves the Wayseer text canon from `wayseer00/main:canon/INTERDEPENDENT_WAY.txt`. The transferred repository copy at `canon/the_interdependent_way.md` is recovery-only and is recorded as a fallback when used.
+- `scripts/parse-canon.mjs` generates units, line ranges, note text, relationships, and SHA-256 digests from either Markdown-style recovery mirrors or the plain-text canonical file.
 - `scripts/fetch-github-org.mjs` discovers every public organization repository and merges GitHub facts with `.interdependency/project.yml` or reviewed central overrides.
 - Pagefind indexes the generated site after Eleventy finishes.
 

scripts/fetch-canon.mjs

@@ -10,33 +10,70 @@ import { mkdir, readFile, writeFile } from 'node:fs/promises';
 // === END MODULE_BUILD ===
 // === BOUNDARIES ===
 // id: canon_network_boundary
-//   network: read-only HTTPS request to raw.githubusercontent.com
+//   network: read-only HTTPS request to allowlisted GitHub API and raw content endpoints
 //   storage: writes generated snapshots beneath src/_data/snapshots
 //   failure: falls back to the repository mirror and records fallback=true
 // === END BOUNDARIES ===
 
 const canonical = {
-  repository: 'wayseer00/wayseer.github.io',
-  path: 'canon/the_interdependent_way.md',
+  repository: 'wayseer00/main',
+  path: 'canon/INTERDEPENDENT_WAY.txt',
   branch: 'main',
-  url: 'https://raw.githubusercontent.com/wayseer00/wayseer.github.io/main/canon/the_interdependent_way.md'
+  webUrl: 'https://github.com/wayseer00/main/blob/main/canon/INTERDEPENDENT_WAY.txt'
 };
 const localMirror = 'canon/the_interdependent_way.md';
+const githubApiOrigin = 'https://api.github.com';
+const rawOrigin = 'https://raw.githubusercontent.com';
+const allowedOrigins = new Set([githubApiOrigin, rawOrigin]);
+const githubHeaders = ['-H', 'Accept: application/vnd.github+json', '-H', 'X-GitHub-Api-Version: 2022-11-28'];
+if (process.env.GITHUB_TOKEN) githubHeaders.push('-H', `Authorization: Bearer ${process.env.GITHUB_TOKEN}`);
 
-function fetchRemote() {
-  if (process.env.OFFLINE === '1') throw new Error('offline requested');
-  return execFileSync('curl', ['-fsSL', '--retry', '2', '--max-time', '30', canonical.url], {
+function curlText(target, extraHeaders = []) {
+  const url = target instanceof URL ? target : new URL(target);
+  if (url.protocol !== 'https:' || !allowedOrigins.has(url.origin)) {
+    throw new Error(`refusing non-allowlisted canon target: ${url.origin}`);
+  }
+  return execFileSync('curl', ['-fsSL', '--retry', '2', '--max-time', '30', ...extraHeaders, url.href], {
     encoding: 'utf8',
     stdio: ['ignore', 'pipe', 'pipe']
   });
 }
 
+function githubApiUrl(pathname, search = {}) {
+  const url = new URL(pathname, githubApiOrigin);
+  for (const [key, value] of Object.entries(search)) url.searchParams.set(key, String(value));
+  return url;
+}
+
+function getJson(target) {
+  return JSON.parse(curlText(target, githubHeaders));
+}
+
+function fetchRemote() {
+  if (process.env.OFFLINE === '1') throw new Error('offline requested');
+  const [owner, repo] = canonical.repository.split('/');
+  const encodedOwner = encodeURIComponent(owner);
+  const encodedRepo = encodeURIComponent(repo);
+  const encodedPath = canonical.path.split('/').map(segment => encodeURIComponent(segment)).join('/');
+  const apiBase = `/repos/${encodedOwner}/${encodedRepo}`;
+  const commitInfo = getJson(githubApiUrl(`${apiBase}/commits/${encodeURIComponent(canonical.branch)}`));
+  const commit = commitInfo.sha;
+  if (!/^[a-f0-9]{40}$/i.test(commit)) throw new Error('canon branch did not resolve to a commit SHA');
+  const fileInfo = getJson(githubApiUrl(`${apiBase}/contents/${encodedPath}`, { ref: commit }));
+  if (fileInfo.type !== 'file' || !fileInfo.sha) throw new Error('canon path did not resolve to a file blob');
+  const resolvedUrl = new URL(`/${encodedOwner}/${encodedRepo}/${commit}/${encodedPath}`, rawOrigin);
+  const text = curlText(resolvedUrl);
+  return { text, commit, blob: fileInfo.sha, resolvedUrl: resolvedUrl.href };
+}
+
 await mkdir('src/_data/snapshots', { recursive: true });
 let text;
 let fallback = false;
 let retrievalError = null;
+let remote = { commit: null, blob: null, resolvedUrl: null };
 try {
-  text = fetchRemote();
+  remote = fetchRemote();
+  text = remote.text;
 } catch (error) {
   fallback = true;
   retrievalError = String(error?.message || error);
@@ -51,6 +88,9 @@ try {
 const contentSha256 = createHash('sha256').update(text).digest('hex');
 const metadata = {
   ...canonical,
+  commit: remote.commit,
+  blob: remote.blob,
+  resolvedUrl: remote.resolvedUrl,
   retrievedAt: new Date().toISOString(),
   contentSha256,
   fallback,

scripts/parse-canon.mjs

@@ -9,7 +9,7 @@ import slugify from 'slugify';
 //   tests: tests/canon-integrity.test.mjs
 // === END MODULE_BUILD ===
 
-const parserVersion = '0.3.0';
+const parserVersion = '0.4.1';
 const provenance = JSON.parse(await readFile('src/_data/snapshots/canon.provenance.json', 'utf8'));
 const raw = await readFile('src/_data/snapshots/canon.last-known-good.md', 'utf8');
 const text = raw.replace(/^---\n[\s\S]*?\n---\n/, '');
@@ -19,7 +19,6 @@ const units = [];
 const sections = [];
 let current = null;
 let sectionId = 'source';
-const articleBySection = new Map();
 
 function slug(value) {
   return slugify(value, { lower: true, strict: true }) || 'unit';
@@ -30,36 +29,69 @@ function boundedRouteSlug(id) {
   const suffix = createHash('sha256').update(id).digest('hex').slice(0, 10);
   return `${candidate.slice(0, 84).replace(/-+$/, '')}-${suffix}`;
 }
+function detectHeading(line) {
+  const markdown = /^(#{1,6})\s+(.+?)\s*$/.exec(line);
+  if (markdown) return { level: markdown[1].length, title: markdown[2].replace(/#+$/, '').trim() };
+  const title = line.trim();
+  if (!title) return null;
+  if (title === 'The Interdependent Way') return { level: 1, title };
+  if (/^(Awakening|The Interdefinables|Human consciousness emerges from|Preamble|Etiquette of the Body Politic)$/i.test(title)) {
+    return { level: 2, title };
+  }
+  if (/^Rights[\w\s’'&\-⁰¹²³⁴⁵⁶⁷⁸⁹]+of The Way[⁰¹²³⁴⁵⁶⁷⁸⁹]*$/i.test(title)) return { level: 2, title };
+  if (/^Addendum:\s+.+$/i.test(title)) return { level: 2, title };
+  if (/^Article\s+(One|Two|Three|Four|Five|Six|Seven|Eight)(?:\s+\([^)]+\))?$/i.test(title)) return { level: 3, title };
+  if (/^(Binary essences meaningfully, divided; then, rooted\.|Trinary perceptual focal states of complex system spirals:.+|Trinary states of social perception:|Archetype passions of possession\..+|Summary|One-sentence takeaway \(exactly as previously given\))$/i.test(title)) {
+    return { level: 3, title };
+  }
+  return null;
+}
+function extractNotes(content) {
+  const notes = [];
+  for (const line of content.split(/\r?\n/)) {
+    const bracket = /^\s*\[([^\]]+)\]\s+(.+)$/.exec(line);
+    if (bracket) {
+      notes.push({ marker: `[${bracket[1]}]`, text: bracket[2].trim() });
+      continue;
+    }
+    const superscript = /^\s*>?\s*([⁰¹²³⁴⁵⁶⁷⁸⁹]+)\s*(.+)$/.exec(line);
+    if (superscript) {
+      notes.push({ marker: superscript[1], text: superscript[2].trim() });
+      continue;
+    }
+    const digit = /^\s*>?\s*(\d+)\s+(.+)$/.exec(line);
+    if (digit) notes.push({ marker: digit[1], text: digit[2].trim() });
+  }
+  return notes;
+}
+function extractNoteMarkers(content) {
+  const markers = [];
+  for (const match of content.matchAll(/\[[^\]]+\]|[⁰¹²³⁴⁵⁶⁷⁸⁹]+/g)) markers.push(match[0]);
+  return [...new Set(markers)];
+}
 function finish(endLine) {
   if (!current) return;
   current.endLine = endLine;
   current.content = current.lines.join('\n').trim();
   current.hash = createHash('sha256').update(current.content).digest('hex');
-  const notePattern = /^\s*\[([^\]]+)\]\s+(.+)$/gm;
-  current.notes = [...current.content.matchAll(notePattern)].map(match => ({ marker: `[${match[1]}]`, text: match[2].trim() }));
-  current.noteMarkers = [...new Set([...current.content.matchAll(/\[([^\]]+)\]/g)].map(match => `[${match[1]}]`))];
+  current.notes = extractNotes(current.content);
+  current.noteMarkers = extractNoteMarkers(current.content);
   units.push(current);
 }
 
 for (let index = 0; index < lines.length; index += 1) {
-  const heading = /^(#{1,6})\s+(.+?)\s*$/.exec(lines[index]);
+  const heading = detectHeading(lines[index]);
   if (!heading) {
     if (current) current.lines.push(lines[index]);
     continue;
   }
   finish(index);
-  const level = heading[1].length;
-  const title = heading[2].replace(/#+$/, '').trim();
-  if (level <= 3) {
+  const { level, title } = heading;
+  if (level <= 2) {
     sectionId = slug(title).replace(/^the-/, '');
     if (!sections.some(section => section.id === sectionId)) sections.push({ id: sectionId, title, level, line: index + 1 });
   }
-  let localId = slug(title);
-  if (/^article\s+/i.test(title)) {
-    const count = (articleBySection.get(sectionId) || 0) + 1;
-    articleBySection.set(sectionId, count);
-    localId = `article-${count}`;
-  }
+  const localId = slug(title);
   current = {
     id: `${sectionId}.${localId}`,
     title,

scripts/validate-content.mjs

@@ -9,9 +9,10 @@ import { access, readFile } from 'node:fs/promises';
 
 const canon = JSON.parse(await readFile('src/_data/generated/canon.json', 'utf8'));
 const repos = JSON.parse(await readFile('src/_data/generated/repos.json', 'utf8'));
-if (canon.source.repository !== 'wayseer00/wayseer.github.io') throw new Error(`unexpected canon repository: ${canon.source.repository}`);
-if (canon.source.path !== 'canon/the_interdependent_way.md') throw new Error(`unexpected canon path: ${canon.source.path}`);
+if (canon.source.repository !== 'wayseer00/main') throw new Error(`unexpected canon repository: ${canon.source.repository}`);
+if (canon.source.path !== 'canon/INTERDEPENDENT_WAY.txt') throw new Error(`unexpected canon path: ${canon.source.path}`);
 if (!canon.source.contentSha256 || canon.source.contentSha256.length !== 64) throw new Error('canon missing SHA-256 digest');
+if (!canon.source.fallback && (!canon.source.commit || !canon.source.blob)) throw new Error('remote canon provenance missing commit or blob SHA');
 if (!canon.units.length || canon.units.some(unit => !unit.hash || !unit.id)) throw new Error('canon units missing identity or hash');
 if (repos.publicRepoCount !== repos.generatedRouteCount) throw new Error('repo route mismatch');
 if (new Set(repos.repositories.map(repo => repo.slug)).size !== repos.repositories.length) throw new Error('duplicate project slug');

src/source/unit.njk

@@ -9,5 +9,5 @@ title: "Source: {{ unit.title }}"
 ---
 <nav class="breadcrumb" aria-label="Breadcrumb"><a href="/">Home</a> / <a href="/way/{{ unit.routeSlug }}/">{{ unit.title }}</a> / Exact source</nav>
 <header class="page-head"><p class="eyebrow">Exact source · deliberate depth</p><h1>{{ unit.title }}</h1><p class="lede">Verbatim source content and machine-verifiable provenance. Commentary elsewhere on this site is subordinate to this layer.</p></header>
-<dl class="meta provenance"><dt>Canonical repository alias</dt><dd>{{ generated.canon.source.repository }}</dd><dt>Path</dt><dd>{{ generated.canon.source.path }}</dd><dt>Branch</dt><dd>{{ generated.canon.source.branch }}</dd><dt>Retrieved</dt><dd>{{ generated.canon.source.retrievedAt }}</dd><dt>Recovery mirror used</dt><dd>{{ generated.canon.source.fallback }}</dd><dt>Canonical unit ID</dt><dd><code>{{ unit.id }}</code></dd><dt>Stable route</dt><dd><code>{{ unit.routeSlug }}</code></dd><dt>Source lines</dt><dd>{{ unit.startLine }}–{{ unit.endLine }}</dd><dt>Unit digest</dt><dd><code>{{ unit.hash }}</code></dd><dt>Document digest</dt><dd><code>{{ generated.canon.source.contentSha256 }}</code></dd></dl>
+<dl class="meta provenance"><dt>Canonical repository</dt><dd>{{ generated.canon.source.repository }}</dd><dt>Path</dt><dd>{{ generated.canon.source.path }}</dd><dt>Branch</dt><dd>{{ generated.canon.source.branch }}</dd><dt>Resolved commit</dt><dd><code>{{ generated.canon.source.commit or 'fallback mirror' }}</code></dd><dt>Blob</dt><dd><code>{{ generated.canon.source.blob or 'fallback mirror' }}</code></dd><dt>Retrieved</dt><dd>{{ generated.canon.source.retrievedAt }}</dd><dt>Recovery mirror used</dt><dd>{{ generated.canon.source.fallback }}</dd><dt>Canonical unit ID</dt><dd><code>{{ unit.id }}</code></dd><dt>Stable route</dt><dd><code>{{ unit.routeSlug }}</code></dd><dt>Source lines</dt><dd>{{ unit.startLine }}–{{ unit.endLine }}</dd><dt>Unit digest</dt><dd><code>{{ unit.hash }}</code></dd><dt>Document digest</dt><dd><code>{{ generated.canon.source.contentSha256 }}</code></dd></dl>
 <pre class="source-block">{{ unit.content }}</pre>

tests/canon-integrity.test.mjs

@@ -4,9 +4,13 @@ import { readFile } from 'node:fs/promises';
 
 test('canon data preserves Wayseer identity, provenance, and stable unit evidence', async () => {
   const canon = JSON.parse(await readFile('src/_data/generated/canon.json', 'utf8'));
-  assert.equal(canon.source.repository, 'wayseer00/wayseer.github.io');
-  assert.equal(canon.source.path, 'canon/the_interdependent_way.md');
+  assert.equal(canon.source.repository, 'wayseer00/main');
+  assert.equal(canon.source.path, 'canon/INTERDEPENDENT_WAY.txt');
   assert.match(canon.source.contentSha256, /^[a-f0-9]{64}$/);
+  if (!canon.source.fallback) {
+    assert.match(canon.source.commit, /^[a-f0-9]{40}$/);
+    assert.match(canon.source.blob, /^[a-f0-9]{40}$/);
+  }
   assert.ok(canon.units.length > 0);
   const routes = new Set();
   for (const unit of canon.units) {