docrev 0.9.15 → 0.9.16

package/dev_notes/stress2/build_adversarial.ts

@@ -1,186 +0,0 @@
-/**
- * Build an adversarial DOCX with hand-crafted commentRangeStart/End
- * markers that probe whether docrev locates comments by *real*
- * anchor (the highlighted run text, taken from the docx XML) or by
- * guesswork. Each comment is designed to expose a specific failure
- * mode if the matcher were not anchor-aware.
- */
-import AdmZip from 'adm-zip';
-import path from 'path';
-
-const out = path.resolve('dev_notes/stress2/adversarial.docx');
-
-// Sentence with: a triplicated word, unicode look-alikes, mid-word
-// hyphenation, and embedded XML-special chars in the *prose* (escaped).
-const paragraphs: { text: string; comments?: { id: string; on: string }[] }[] = [
-  // heading
-  { text: 'Methods', comments: [] },
-
-  // p0: single highlight, easy
-  { text: 'The methods section describes our approach in detail.',
-    comments: [{ id: '0', on: 'methods section' }] },
-
-  // p1: word "model" appears 3x — anchor must pin the SECOND occurrence
-  { text: 'The model is fitted, the model is checked, the model is reported.',
-    comments: [{ id: '1', on: 'model' /* second occurrence */ }] },
-
-  // p2: empty anchor (zero-width comment, classic Word "insert here")
-  { text: 'Reviewers often place a marker between two sentences. Like this. Then continue.',
-    comments: [{ id: '2', on: '' }] },
-
-  // p3: anchor spanning across multiple runs (formatting break)
-  { text: 'Our results show that p < 0.001 across all conditions.',
-    comments: [{ id: '3', on: 'p < 0.001' }] },
-
-  // p4: text containing literal angle brackets that would break a naive
-  // [^<]* regex — anchor includes "(<1825)"
-  { text: 'Trade volumes pre-industrial (<1825) were modest.',
-    comments: [{ id: '4', on: '(<1825)' }] },
-
-  // p5: very long anchor (full sentence) — matcher must still place it
-  { text: 'We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan.',
-    comments: [{ id: '5', on: 'We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan.' }] },
-
-  // p6: anchor on punctuation only — should fall back to context
-  { text: 'See Table 1 for details; numbers are rounded.',
-    comments: [{ id: '6', on: ';' }] },
-
-  // p7: two overlapping comment ranges share a word
-  { text: 'The overrepresented species are listed in Appendix A.',
-    comments: [
-      { id: '7', on: 'overrepresented species' },
-      { id: '8', on: 'overrepresented' },
-    ] },
-
-  // p8: anchor that exists VERBATIM elsewhere in the doc — context disambiguates
-  { text: 'The cohort was small. Limitations are discussed in Section 5.',
-    comments: [{ id: '9', on: 'small' }] },
-  { text: 'The effect was small but significant.',
-    comments: [{ id: '10', on: 'small' }] },
-
-  // p9: heading paragraph (<w:pStyle w:val="Heading1"/>)
-  { text: 'Discussion', comments: [], /* heading marker handled below */ },
-  { text: 'In this section we situate the findings in prior literature.',
-    comments: [{ id: '11', on: 'situate the findings' }] },
-];
-
-function escapeXml(s: string): string {
-  return s.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;')
-          .replace(/"/g, '&quot;').replace(/'/g, '&apos;');
-}
-
-function buildParagraphXml(p: typeof paragraphs[0], isHeading: boolean): string {
-  const text = p.text;
-  const comments = p.comments || [];
-
-  if (comments.length === 0) {
-    return `<w:p>${isHeading ? '<w:pPr><w:pStyle w:val="Heading1"/></w:pPr>' : ''}<w:r><w:t xml:space="preserve">${escapeXml(text)}</w:t></w:r></w:p>`;
-  }
-
-  // Plan ranges: each comment marks [start..end] character offsets into `text`.
-  // Empty anchors place start=end at first sentence boundary.
-  type Range = { id: string; start: number; end: number };
-  const ranges: Range[] = [];
-  for (const c of comments) {
-    if (c.on === '') {
-      const dotIdx = text.indexOf('.');
-      const pos = dotIdx >= 0 ? dotIdx + 1 : 0;
-      ranges.push({ id: c.id, start: pos, end: pos });
-      continue;
-    }
-    if (c.id === '1') {
-      // "model" — pick the SECOND occurrence
-      const first = text.indexOf('model');
-      const second = text.indexOf('model', first + 1);
-      ranges.push({ id: c.id, start: second, end: second + 'model'.length });
-      continue;
-    }
-    const start = text.indexOf(c.on);
-    if (start < 0) throw new Error(`anchor not found: ${c.on}`);
-    ranges.push({ id: c.id, start, end: start + c.on.length });
-  }
-
-  // Build event list: at each char boundary we may need to emit
-  // <w:commentRangeStart/> or <w:commentRangeEnd/>.
-  type Event = { pos: number; kind: 'start' | 'end'; id: string };
-  const events: Event[] = [];
-  for (const r of ranges) {
-    events.push({ pos: r.start, kind: 'start', id: r.id });
-    events.push({ pos: r.end, kind: 'end', id: r.id });
-  }
-  // Emit ends before starts at same position, so an empty anchor's start=end
-  // ordering keeps a zero-width range
-  events.sort((a, b) => a.pos - b.pos || (a.kind === 'end' ? -1 : 1));
-
-  let xml = `<w:p>${isHeading ? '<w:pPr><w:pStyle w:val="Heading1"/></w:pPr>' : ''}`;
-  let cursor = 0;
-  for (const ev of events) {
-    if (ev.pos > cursor) {
-      xml += `<w:r><w:t xml:space="preserve">${escapeXml(text.slice(cursor, ev.pos))}</w:t></w:r>`;
-      cursor = ev.pos;
-    }
-    xml += ev.kind === 'start'
-      ? `<w:commentRangeStart w:id="${ev.id}"/>`
-      : `<w:commentRangeEnd w:id="${ev.id}"/><w:r><w:commentReference w:id="${ev.id}"/></w:r>`;
-  }
-  if (cursor < text.length) {
-    xml += `<w:r><w:t xml:space="preserve">${escapeXml(text.slice(cursor))}</w:t></w:r>`;
-  }
-  xml += `</w:p>`;
-  return xml;
-}
-
-const headingTexts = new Set(['Methods', 'Discussion']);
-const documentBody = paragraphs.map(p => buildParagraphXml(p, headingTexts.has(p.text))).join('');
-
-const documentXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
-  <w:body>
-    ${documentBody}
-    <w:sectPr/>
-  </w:body>
-</w:document>`;
-
-const allComments = paragraphs.flatMap(p => p.comments || []);
-
-const commentsXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<w:comments xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
-${allComments.map(c => `  <w:comment w:id="${c.id}" w:author="Reviewer" w:initials="R" w:date="2026-01-01T00:00:00Z"><w:p><w:r><w:t>Comment ${c.id} on &quot;${escapeXml(c.on)}&quot; — text contains <embedded brackets and &amp;.</w:t></w:r></w:p></w:comment>`.replace('<embedded', '&lt;embedded')).join('\n')}
-</w:comments>`;
-
-const contentTypesXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
-  <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
-  <Default Extension="xml" ContentType="application/xml"/>
-  <Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
-  <Override PartName="/word/comments.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml"/>
-  <Override PartName="/word/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml"/>
-</Types>`;
-
-const rootRelsXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
-  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
-</Relationships>`;
-
-const docRelsXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
-  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments" Target="comments.xml"/>
-  <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>
-</Relationships>`;
-
-const stylesXml = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
-  <w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/></w:style>
-</w:styles>`;
-
-const zip = new AdmZip();
-zip.addFile('[Content_Types].xml', Buffer.from(contentTypesXml, 'utf8'));
-zip.addFile('_rels/.rels', Buffer.from(rootRelsXml, 'utf8'));
-zip.addFile('word/document.xml', Buffer.from(documentXml, 'utf8'));
-zip.addFile('word/comments.xml', Buffer.from(commentsXml, 'utf8'));
-zip.addFile('word/styles.xml', Buffer.from(stylesXml, 'utf8'));
-zip.addFile('word/_rels/document.xml.rels', Buffer.from(docRelsXml, 'utf8'));
-zip.writeZip(out);
-
-console.log(`wrote ${out}`);
-console.log(`comments: ${allComments.length}`);

package/dev_notes/stress2/drift_matcher.ts

@@ -1,62 +0,0 @@
-/**
- * Run anchors from the adversarial docx against a HEAVILY DRIFTED
- * markdown and report match quality per comment.
- */
-import { extractCommentAnchors } from '../../lib/word-extraction.js';
-import { findAnchorInText, classifyStrategy } from '../../lib/anchor-match.js';
-
-const docx = 'dev_notes/stress2/adversarial.docx';
-
-// Drifted markdown — same comments need to land on this.
-//  - p0 paraphrased
-//  - p1 reordered, only TWO occurrences of "model"
-//  - p2 prose lightly edited, sentence boundary preserved
-//  - p3 prose changed slightly: "p < 0.001 (n=412)"
-//  - p4 prose moved (<1825)
-//  - p5 mostly intact
-//  - p6 entire sentence rewritten ("Round numbers are reported in Table 1.")
-//  - p7 unchanged
-//  - p8/p9 unchanged
-//  - p10/p11 unchanged
-const drifted = [
-  '# Methods', '',
-  'Below we describe our methodology in detail.', '',
-  'The model is fitted; later, the model is reported.', '',
-  'Reviewers often place a marker between two sentences. Like this. Then continue.', '',
-  'Our results show that p < 0.001 (n=412) across all conditions.', '',
-  'Trade volumes were modest pre-industrial (<1825).', '',
-  'We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan.', '',
-  'Round numbers are reported in Table 1.', '',
-  'The overrepresented species are listed in Appendix A.', '',
-  'The cohort was small. Limitations are discussed in Section 5.',
-  'The effect was small but significant.', '',
-  '# Discussion', '',
-  'In this section we situate the findings in prior literature.',
-].join('\n');
-
-const { anchors } = await extractCommentAnchors(docx);
-
-const sorted = [...anchors.entries()].sort((a, b) => Number(a[0]) - Number(b[0]));
-
-const tally = { clean: 0, drift: 0, 'context-only': 0, ambiguous: 0, unmatched: 0 };
-
-console.log('id │ quality       │ strategy            │ #hits │ anchor');
-console.log('───┼───────────────┼─────────────────────┼───────┼──────────────────────');
-for (const [id, a] of sorted) {
-  const r = findAnchorInText(a.anchor, drifted, a.before, a.after);
-  let q: keyof typeof tally = classifyStrategy(r.strategy, r.occurrences.length) as any;
-  if (r.occurrences.length > 1) q = 'ambiguous';
-  tally[q]++;
-  const tag = a.isEmpty ? '∅' : a.anchor.length > 30 ? a.anchor.slice(0, 27) + '...' : a.anchor;
-  console.log(`${id.padStart(2)} │ ${q.padEnd(13)} │ ${r.strategy.padEnd(19)} │ ${String(r.occurrences.length).padStart(5)} │ ${JSON.stringify(tag)}`);
-}
-
-console.log('\nTally:', tally);
-
-// Also confirm: comment #6 (";") will fail anchor-direct match and force
-// context fallback (because the original sentence was rewritten).
-console.log('\nComment #6 (\";\") — sentence rewritten in drifted md.');
-const c6 = anchors.get('6')!;
-const r6 = findAnchorInText(c6.anchor, drifted, c6.before, c6.after);
-console.log(`  strategy=${r6.strategy}, hits=${r6.occurrences.length}`);
-console.log(`  ${r6.occurrences.length > 0 ? 'placed via fallback' : 'left for manual placement'}`);

package/dev_notes/stress2/probe_anchors.ts

@@ -1,35 +0,0 @@
-/**
- * Probe: do extracted anchors come from `<w:commentRangeStart/End>`
- * markers (i.e. real anchors), and does each comment carry a unique
- * docPosition that disambiguates duplicate prose?
- */
-import { extractCommentAnchors } from '../../lib/word-extraction.js';
-
-const docx = 'dev_notes/stress2/adversarial.docx';
-const { anchors, fullDocText } = await extractCommentAnchors(docx);
-
-console.log(`Doc text length: ${fullDocText.length}`);
-console.log(`Anchors extracted: ${anchors.size}\n`);
-
-const sorted = [...anchors.entries()].sort((a, b) => Number(a[0]) - Number(b[0]));
-
-for (const [id, a] of sorted) {
-  const tag = a.isEmpty ? '∅(empty)' : JSON.stringify(a.anchor);
-  console.log(`#${id}  pos=${String(a.docPosition).padStart(4)}  anchor=${tag}`);
-  if (a.before) console.log(`       before=${JSON.stringify(a.before.slice(-40))}`);
-  if (a.after)  console.log(`       after =${JSON.stringify(a.after.slice(0, 40))}`);
-}
-
-// Sanity: comment 1 should pin the SECOND occurrence of "model"
-const c1 = anchors.get('1')!;
-const firstModel = fullDocText.indexOf('model');
-const secondModel = fullDocText.indexOf('model', firstModel + 1);
-console.log(`\nComment #1 expectation: pin SECOND "model" at pos ${secondModel}`);
-console.log(`Comment #1 actual  docPosition=${c1.docPosition}`);
-console.log(`Match: ${c1.docPosition === secondModel ? 'YES (real-anchor)' : 'NO'}`);
-
-// Comment 7 vs 8: overlapping ranges, both anchored on "overrepresented..."
-const c7 = anchors.get('7')!;
-const c8 = anchors.get('8')!;
-console.log(`\nComment #7 anchor: ${JSON.stringify(c7.anchor)} (expected "overrepresented species")`);
-console.log(`Comment #8 anchor: ${JSON.stringify(c8.anchor)} (expected "overrepresented")`);

package/dev_notes/stress2/project/discussion.before.md

@@ -1,3 +0,0 @@
-# Discussion
-
-In this section we situate the findings in prior literature.

package/dev_notes/stress2/project/discussion.md

@@ -1,3 +0,0 @@
-# Discussion
-
-In this section we {>>Reviewer: Comment 11 on "situate the findings" — text contains <embedded brackets and &.<<}situate the findings in prior literature.

package/dev_notes/stress2/project/methods.before.md

@@ -1,20 +0,0 @@
-# Methods
-
-Below we describe our methodology in detail.
-
-The model is fitted; later, the model is reported.
-
-Reviewers often place a marker between two sentences. Like this. Then continue.
-
-Our results show that p < 0.001 (n=412) across all conditions.
-
-Trade volumes were modest pre-industrial (<1825).
-
-We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan.
-
-Round numbers are reported in Table 1.
-
-The overrepresented species are listed in Appendix A.
-
-The cohort was small. Limitations are discussed in Section 5.
-The effect was small but significant.

package/dev_notes/stress2/project/methods.md

@@ -1,20 +0,0 @@
-# Methods
-
-Below we describe{>>Reviewer: Comment 0 on "methods section" — text contains <embedded brackets and &.<<} our methodology in detail.
-
-The {>>Reviewer: Comment 1 on "model" — text contains <embedded brackets and &.<<}model is fitted; later, the model is reported.
-
-Reviewers often place a marker between two sentences. Like this. Then{>>Reviewer: Comment 2 on "" — text contains <embedded brackets and &.<<} continue.
-
-Our results show that {>>Reviewer: Comment 3 on "p < 0.001" — text contains <embedded brackets and &.<<}p < 0.001 (n=412) across all conditions.
-
-Trade volumes were modest pre-industrial {>>Reviewer: Comment 4 on "(<1825)" — text contains <embedded brackets and &.<<}(<1825).
-
-{>>Reviewer: Comment 5 on "We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan." — text contains <embedded brackets and &.<<}We used a hierarchical Bayesian model with weakly informative priors and Hamiltonian Monte Carlo sampling implemented in Stan.
-
-Round numbers are reported{>>Reviewer: Comment 6 on ";" — text contains <embedded brackets and &.<<} in Table 1.
-
-The {>>Reviewer: Comment 7 on "overrepresented species" — text contains <embedded brackets and &.<<}overrepresented{>>Reviewer: Comment 8 on "overrepresented" — text contains <embedded brackets and &.<<} species are listed in Appendix A.
-
-The cohort was {>>Reviewer: Comment 9 on "small" — text contains <embedded brackets and &.<<}small. Limitations are discussed in Section 5.
-The effect was {>>Reviewer: Comment 10 on "small" — text contains <embedded brackets and &.<<}small but significant.

package/dev_notes/stress2/project/rev.yaml

@@ -1,5 +0,0 @@
-title: stress2
-authors: []
-sections:
-  - methods
-  - discussion

package/dev_notes/stress2/project/sections.yaml

@@ -1,4 +0,0 @@
-version: 1
-sections:
-  methods.md: Methods
-  discussion.md: Discussion

package/dev_notes/stress2/sections.yaml

@@ -1,5 +0,0 @@
-sections:
-  - file: methods.md
-    header: Methods
-  - file: discussion.md
-    header: Discussion

package/dev_notes/stress2/trace_placement.ts

@@ -1,50 +0,0 @@
-/**
- * Trace exactly where insertCommentsIntoMarkdown places each comment.
- * Reproduces the methods.md sync to see if disambiguation works.
- */
-import { extractCommentAnchors, extractWordComments } from '../../lib/word-extraction.js';
-import { insertCommentsIntoMarkdown } from '../../lib/import.js';
-import * as fs from 'fs';
-
-const docx = 'dev_notes/stress2/adversarial.docx';
-const md = fs.readFileSync('dev_notes/stress2/project/methods.before.md', 'utf-8');
-
-const { anchors } = await extractCommentAnchors(docx);
-const comments = await extractWordComments(docx);
-
-// Filter to methods (everything except #11)
-const methodsComments = comments.filter((c: any) => c.id !== '11');
-
-console.log('Markdown length:', md.length);
-console.log('Comments to place:', methodsComments.length);
-
-const smallPositions: number[] = [];
-let i = 0;
-while ((i = md.indexOf('small', i)) !== -1) {
-  smallPositions.push(i);
-  i += 5;
-}
-console.log('"small" occurrences in md at:', smallPositions);
-for (const p of smallPositions) {
-  console.log(`  pos ${p}: ...${JSON.stringify(md.slice(Math.max(0, p - 30), p + 30))}...`);
-}
-
-console.log('\nDocx anchor data for #9 and #10:');
-for (const id of ['9', '10']) {
-  const a = anchors.get(id)!;
-  console.log(`  #${id}: docPos=${a.docPosition}, before=${JSON.stringify(a.before.slice(-30))}, after=${JSON.stringify(a.after.slice(0, 30))}`);
-}
-
-// Run with quiet:false to see warnings
-const out = insertCommentsIntoMarkdown(md, methodsComments, anchors, {
-  quiet: false,
-  wrapAnchor: false,
-});
-
-// Locate both inserted comment blocks
-const block9 = out.indexOf('Comment 9 on');
-const block10 = out.indexOf('Comment 10 on');
-console.log(`\n#9 inserted at md offset: ${block9}`);
-console.log(`#10 inserted at md offset: ${block10}`);
-console.log(`Surrounding #9: ${JSON.stringify(out.slice(Math.max(0, block9 - 30), block9 + 50))}`);
-console.log(`Surrounding #10: ${JSON.stringify(out.slice(Math.max(0, block10 - 30), block10 + 50))}`);

package/dev_notes/stresstest_boundaries.ts

@@ -1,27 +0,0 @@
-import { extractCommentAnchors } from '../lib/import.js';
-
-const docx = 'C:/GillesC/tmp/docrev-stress/reviewed.docx';
-const { fullDocText } = await extractCommentAnchors(docx);
-
-function findSectionHeader(text: string, header: string): number {
-  const needle = header.toLowerCase().trim();
-  const lower = text.toLowerCase();
-  let idx = 0;
-  while ((idx = lower.indexOf(needle, idx)) !== -1) {
-    const after = text.slice(idx + needle.length, idx + needle.length + 5);
-    if (!after.startsWith(':') && !after.startsWith(' :')) return idx;
-    idx++;
-  }
-  return -1;
-}
-
-const headers = ['Abstract', 'Introduction', 'Methods', 'Results', 'Discussion', 'Conclusion', 'References', 'Supplementary Materials'];
-const found = headers.map(h => ({ h, idx: findSectionHeader(fullDocText, h) }))
-  .filter(x => x.idx >= 0)
-  .sort((a, b) => a.idx - b.idx);
-
-console.log('Sorted boundary positions found:');
-for (const f of found) {
-  const ctx = fullDocText.slice(Math.max(0, f.idx - 20), f.idx + 30).replace(/\s+/g, ' ');
-  console.log(`  ${f.h.padEnd(25)} @ ${f.idx}  ctx: ...${ctx}...`);
-}

package/dev_notes/stresstest_drift_apply.ts

@@ -1,43 +0,0 @@
-// Apply targeted drift edits to project-drifted/abstract.md and methods.md
-import * as fs from 'fs';
-
-const dir = 'C:/GillesC/tmp/docrev-stress/project-drifted';
-
-function edit(file: string, edits: Array<[string, string]>) {
-  const p = `${dir}/${file}`;
-  let t = fs.readFileSync(p, 'utf-8');
-  for (const [from, to] of edits) {
-    if (!t.includes(from)) {
-      console.error(`!! ${file}: pattern not found: "${from.slice(0, 60)}"`);
-      continue;
-    }
-    t = t.replace(from, to);
-    console.log(`OK ${file}: replaced "${from.slice(0, 60)}..."`);
-  }
-  fs.writeFileSync(p, t);
-}
-
-// Word swap: 'accelerating' should still be findable via stripped/partial fallback (anchor was a single word, replacing changes the prose)
-// Actually: replacing "accelerating" with "rapid" in the abstract removes the anchor entirely.
-// Some comments have anchor "accelerating" — those should go drift -> unmatched.
-
-edit('abstract.md', [
-  ['accelerating rates', 'rapid rates'],
-  // Numerical drift: this anchor is "0–20 years" / "57%" — both should fail to direct match
-  ['from 17% (0--20 years) to 57%', 'from 15% (0–25 years) to 60%'],
-  // Anchor-spanning rewrite: replace 'Man-made and ruderal habitats functioned as gateways' with 'Anthropogenic habitats acted as entry points'
-  ['Man-made and ruderal habitats functioned as gateways', 'Anthropogenic habitats acted as entry points'],
-  // Number change in big number
-  ['835,891 vegetation plots', '1,200,000 vegetation plots'],
-]);
-
-// Delete an entire paragraph from discussion (so anchors there go unmatched)
-const disc = fs.readFileSync(`${dir}/discussion.md`, 'utf-8');
-// Just append a marker to track that we did NOT delete; instead, we'll insert a new prose block to test that comments still land correctly relative to it.
-// For deletion test, find a known phrase and remove its sentence
-edit('discussion.md', [
-  // Insert a new paragraph at top to force position drift in proportion-based placement
-  ['# Discussion\n', '# Discussion\n\n_NOTE: this paragraph was inserted after review. Just an extra block of prose to push everything downward in the markdown so that proportion-based anchor placement gets stress-tested. We pad with several sentences to ensure the offset is meaningful and that fuzzy matchers still find the right targets despite this drift._\n\n'],
-]);
-
-console.log('drift applied');

package/dev_notes/stresstest_drift_compare.ts

@@ -1,43 +0,0 @@
-// Compare pristine vs drifted verify-anchors output
-import * as fs from 'fs';
-
-const a = JSON.parse(fs.readFileSync('C:/GillesC/tmp/docrev-stress/pristine.json', 'utf-8'));
-const b = JSON.parse(fs.readFileSync('C:/GillesC/tmp/docrev-stress/drifted.json', 'utf-8'));
-
-console.log('Summary deltas:');
-const keys = Array.from(new Set([...Object.keys(a.summary), ...Object.keys(b.summary)]));
-for (const k of keys) {
-  const av = a.summary[k] ?? 0;
-  const bv = b.summary[k] ?? 0;
-  const delta = bv - av;
-  console.log(`  ${k.padEnd(15)} ${String(av).padStart(4)} -> ${String(bv).padStart(4)}  (delta ${delta >= 0 ? '+' : ''}${delta})`);
-}
-console.log();
-
-// Show comments whose quality changed (especially those that moved to a worse bucket)
-const aMap = new Map(a.comments.map((c: any) => [c.id, c]));
-console.log('Quality changes:');
-let regressions = 0;
-let improvements = 0;
-for (const c of b.comments) {
-  const prev = aMap.get(c.id) as any;
-  if (!prev) continue;
-  if (prev.quality !== c.quality) {
-    const dir = qualityRank(c.quality) > qualityRank(prev.quality) ? '⬇' : '⬆';
-    if (dir === '⬇') regressions++; else improvements++;
-    console.log(`  ${dir} #${c.id} [${c.section || '—'}] ${prev.quality}/${prev.strategy} -> ${c.quality}/${c.strategy}  anchor="${(c.anchor || '').slice(0, 35)}"`);
-  }
-}
-console.log();
-console.log(`regressions: ${regressions}  improvements: ${improvements}`);
-
-function qualityRank(q: string): number {
-  switch (q) {
-    case 'clean': return 0;
-    case 'drift': return 1;
-    case 'context-only': return 2;
-    case 'ambiguous': return 1; // ambiguous is sideways, not strictly worse
-    case 'unmatched': return 3;
-    default: return 4;
-  }
-}

package/dev_notes/stresstest_drift_v2.ts

@@ -1,54 +0,0 @@
-// Apply drift edits that actually intersect real comment anchors
-import * as fs from 'fs';
-
-const dir = 'C:/GillesC/tmp/docrev-stress/project-drifted';
-
-function edit(file: string, edits: Array<[string, string]>) {
-  const p = `${dir}/${file}`;
-  let t = fs.readFileSync(p, 'utf-8');
-  for (const [from, to] of edits) {
-    if (!t.includes(from)) {
-      console.error(`!! ${file}: pattern not found: "${from.slice(0, 60)}"`);
-      continue;
-    }
-    t = t.replace(from, to);
-    console.log(`OK ${file}: replaced "${from.slice(0, 60)}..."`);
-  }
-  fs.writeFileSync(p, t);
-}
-
-// Each of these intersects real anchors; expected effect noted.
-edit('abstract.md', [
-  // Title: 3 anchors are 'Patterns of habitat niche expansion' (full title) — but title isn't in abstract.md, it's in YAML frontmatter, so probably already failing
-  // 'overrepresented' is the most common anchor (6 comments). Replace it everywhere.
-  // After this, the word 'overrepresented' is gone → all those comments should go to context-only or unmatched
-  ['overrepresented in more than one habitat type', 'preferentially distributed across habitat types'],
-  // 'undisturbed' appears in 'undisturbed habitat types' → 2 comments
-  ['undisturbed habitat types', 'pristine vegetation communities'],
-  // 'human economies' (3 anchors)
-  ['human economies', 'economic activity'],
-  // 'nutrient-rich'
-  ['nutrient-rich, disturbed habitats', 'anthropic, modified environments'],
-  // 'when residence time was prolonged.' — long anchor, should go to drift / partial-start
-  ['when residence time was prolonged.', 'as residence time increased.'],
-  // 'pervasive' (1 anchor)
-  ['Invasion debt in terms of habitat niche breadth is pervasive', 'Invasion debt in terms of habitat niche breadth is widespread'],
-  // 'alpine habitats' (1 anchor)
-  ['alpine habitats', 'high-altitude environments'],
-  // 'semi-natural vegetation' (2 anchors)
-  ['semi-natural vegetation', 'natural plant communities'],
-  // 'Man-made habitats function as gateways' (1 anchor)
-  ['Man-made habitats function as gateways', 'Anthropogenic environments serve as entry routes'],
-  // 'Invasion debt in terms of habitat niche breadth' (2 anchors)
-  // Already mutated above (pervasive→widespread keeps anchor matchable). Add another small change to test partial-start
-  // 'habitat niche expansion' — anchor for #27
-  ['habitat niche expansion', 'ecological niche broadening'],
-  // ', yet' anchor for #19
-  [', yet', ', however'],
-  // '44' — short numeric anchor
-  ['44%', '53%'],
-  // '17 habitats'
-  ['17 habitats', '18 habitats'],
-]);
-
-console.log('---done');

package/dev_notes/stresstest_inspect.ts

@@ -1,54 +0,0 @@
-import { extractWordComments, extractCommentAnchors } from '../lib/import.js';
-
-const docx = 'C:/GillesC/tmp/docrev-stress/reviewed.docx';
-
-const comments = await extractWordComments(docx);
-const { anchors, fullDocText } = await extractCommentAnchors(docx);
-
-console.log(`comments: ${comments.length}`);
-console.log(`anchors:  ${anchors.size}`);
-console.log(`docText:  ${fullDocText.length} chars`);
-console.log();
-
-const byAuthor: Record<string, number> = {};
-for (const c of comments) byAuthor[c.author] = (byAuthor[c.author] || 0) + 1;
-console.log('by author:', byAuthor);
-console.log();
-
-console.log('first 5 comments:');
-for (const c of comments.slice(0, 5)) {
-  const a = anchors.get(c.id);
-  const pos = a?.docPosition ?? -1;
-  const anchor = (a?.anchor || '').slice(0, 60);
-  const text = c.text.replace(/\s+/g, ' ').slice(0, 80);
-  console.log(`  #${c.id} [${c.author}] pos=${pos} anchor="${anchor}" text="${text}"`);
-}
-console.log();
-console.log('last 3 comments:');
-for (const c of comments.slice(-3)) {
-  const a = anchors.get(c.id);
-  const pos = a?.docPosition ?? -1;
-  const anchor = (a?.anchor || '').slice(0, 60);
-  const text = c.text.replace(/\s+/g, ' ').slice(0, 80);
-  console.log(`  #${c.id} [${c.author}] pos=${pos} anchor="${anchor}" text="${text}"`);
-}
-console.log();
-
-const sectionKeywords = ['Abstract', 'Introduction', 'Methods', 'Results', 'Discussion', 'Conclusion', 'References', 'Acknowledgements', 'Data Availability', 'Author Contributions'];
-console.log('candidate headings:');
-for (const kw of sectionKeywords) {
-  const idx = fullDocText.indexOf(kw);
-  if (idx >= 0) {
-    const context = fullDocText.slice(idx, idx + 80).replace(/\s+/g, ' ');
-    console.log(`  ${kw} @ ${idx}: "${context}"`);
-  }
-}
-
-// Check anchor distribution to understand section spans
-const positions = [...anchors.values()].map(a => a.docPosition).sort((a, b) => a - b);
-console.log();
-console.log(`anchor positions: min=${positions[0]} max=${positions[positions.length-1]} median=${positions[Math.floor(positions.length/2)]}`);
-
-// Check for empty anchors
-const empty = [...anchors.values()].filter(a => a.isEmpty).length;
-console.log(`empty anchors: ${empty}`);