docrev 0.9.13 → 0.9.14

package/dev_notes/stress2/project/methods.md

@@ -1,20 +1,20 @@
-# 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.
+# 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 +1,5 @@
-title: stress2
-authors: []
-sections:
-  - methods
-  - discussion
+title: stress2
+authors: []
+sections:
+  - methods
+  - discussion

package/dev_notes/stress2/project/sections.yaml

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

package/dev_notes/stress2/sections.yaml

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

package/dev_notes/stress2/trace_placement.ts

@@ -1,50 +1,50 @@
-/**
- * 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))}`);
+/**
+ * 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 +1,27 @@
-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}...`);
-}
+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 +1,43 @@
-// 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(`${dir}/discussion.md`, 'utf-8');
-// Just append a marker to track that we did NOT delete; instead, we'll insert a new prose block to test that comments still land correctly relative to it.
-// For deletion test, find a known phrase and remove its sentence
-edit('discussion.md', [
-  // Insert a new paragraph at top to force position drift in proportion-based placement
-  ['# Discussion\n', '# Discussion\n\n_NOTE: this paragraph was inserted after review. Just an extra block of prose to push everything downward in the markdown so that proportion-based anchor placement gets stress-tested. We pad with several sentences to ensure the offset is meaningful and that fuzzy matchers still find the right targets despite this drift._\n\n'],
-]);
-
-console.log('drift applied');
+// Apply targeted drift edits to project-drifted/abstract.md and methods.md
+import * as fs from 'fs';
+
+const dir = 'C:/GillesC/tmp/docrev-stress/project-drifted';
+
+function edit(file: string, edits: Array<[string, string]>) {
+  const p = `${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 +1,43 @@
-// 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;
-  }
-}
+// 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 +1,54 @@
-// 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');
+// 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 +1,54 @@
-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}`);
+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}`);