docrev 0.9.15 → 0.9.17

package/lib/anchor-match.ts

@@ -11,6 +11,8 @@ export type AnchorStrategy =
   | 'stripped'
   | 'partial-start'
   | 'partial-start-stripped'
+  | 'partial-window'
+  | 'partial-window-stripped'
   | 'context-both'
   | 'context-before'
   | 'context-after'
@@ -171,41 +173,69 @@ export function findAnchorInText(
     return { occurrences, matchedAnchor: anchor, strategy: 'stripped', stripped: true };
   }
 
-  // Strategy 4: first N words of anchor (long anchors)
+  // Strategy 4: word window from anchor (prefix or interior).
+  // Sliding the window across the anchor catches the case where the
+  // anchor's prefix has been edited but a chunk in the middle/end
+  // survived intact (e.g. "Sensitivity analyses were performed by
+  // perturbing the prior variance" → drifted "Sensitivity analyses
+  // perturbed the prior variance" still contains "the prior variance").
   const words = anchor.split(/\s+/);
   if (words.length > 3) {
     for (let n = Math.min(6, words.length); n >= 3; n--) {
-      const partialAnchor = words.slice(0, n).join(' ').toLowerCase();
-      if (partialAnchor.length >= 15) {
-        occurrences = findAllOccurrences(textLower, partialAnchor);
-        if (occurrences.length > 0) {
-          return { occurrences, matchedAnchor: words.slice(0, n).join(' '), strategy: 'partial-start' };
+      for (let start = 0; start + n <= words.length; start++) {
+        const window = words.slice(start, start + n).join(' ');
+        const windowLower = window.toLowerCase();
+        if (windowLower.length < 15) continue;
+
+        let occ = findAllOccurrences(textLower, windowLower);
+        if (occ.length > 0) {
+          const strategy: AnchorStrategy = start === 0 ? 'partial-start' : 'partial-window';
+          return { occurrences: occ, matchedAnchor: window, strategy };
         }
-        occurrences = findAllOccurrences(strippedLower, partialAnchor);
-        if (occurrences.length > 0) {
-          return {
-            occurrences,
-            matchedAnchor: words.slice(0, n).join(' '),
-            strategy: 'partial-start-stripped',
-            stripped: true,
-          };
+        occ = findAllOccurrences(strippedLower, windowLower);
+        if (occ.length > 0) {
+          const strategy: AnchorStrategy = start === 0 ? 'partial-start-stripped' : 'partial-window-stripped';
+          return { occurrences: occ, matchedAnchor: window, strategy, stripped: true };
         }
       }
     }
   }
 
-  // Strategy 5: context (before/after) only
+  // Strategy 5: context (before/after) only.
+  //
+  // For a non-empty anchor that already failed every text-based strategy
+  // above, we treat context as a degraded placement: classify it
+  // 'context-only' so callers can warn the user. We also reject
+  // implausible brackets — if both contexts match but the gap between
+  // them is far too small to contain the anchor (e.g. the anchored
+  // sentence was deleted), do not silently land the comment between
+  // the surviving sentences. Return 'failed' so the user is told to
+  // place it manually.
   if (before || after) {
     const beforeLower = before.toLowerCase();
     const afterLower = after.toLowerCase();
+    const anchorLen = anchor.length;
 
     if (before && after) {
       const beforeIdx = textLower.indexOf(beforeLower.slice(-50));
       if (beforeIdx !== -1) {
         const searchStart = beforeIdx + beforeLower.slice(-50).length;
         const afterIdx = textLower.indexOf(afterLower.slice(0, 50), searchStart);
-        if (afterIdx !== -1 && afterIdx - searchStart < 500) {
-          return { occurrences: [searchStart], matchedAnchor: null, strategy: 'context-both' };
+        if (afterIdx !== -1) {
+          const gap = afterIdx - searchStart;
+          // Require the bracket to plausibly contain a remnant of the anchor.
+          // Below 30% of anchor length: anchor was deleted — refuse to place.
+          // Above 2× anchor length + slack: brackets are too far apart, the
+          // matcher has latched onto unrelated repeats of common context.
+          const minGap = Math.floor(anchorLen * 0.3);
+          const maxGap = Math.min(500, anchorLen * 2 + 50);
+          if (gap >= minGap && gap <= maxGap) {
+            return { occurrences: [searchStart], matchedAnchor: null, strategy: 'context-both' };
+          }
+          // Both brackets found but gap implausible: anchor likely deleted.
+          // Don't fall back to single-side context — that would silently
+          // place the comment in the wrong location.
+          return { occurrences: [], matchedAnchor: null, strategy: 'failed' };
         }
       }
     }
@@ -262,6 +292,8 @@ export function classifyStrategy(strategy: AnchorStrategy, occurrences: number):
     case 'stripped':
     case 'partial-start':
     case 'partial-start-stripped':
+    case 'partial-window':
+    case 'partial-window-stripped':
     case 'split-match':
       return 'drift';
     case 'context-both':

package/lib/build.ts

@@ -74,6 +74,7 @@ export interface PdfConfig {
 export interface DocxConfig {
   reference?: string | null;
   keepComments?: boolean;
+  affiliationNewline?: boolean;
   toc?: boolean;
 }
 
@@ -232,7 +233,8 @@ export const DEFAULT_CONFIG: BuildConfig = {
   },
   docx: {
     reference: null,
-    keepComments: true,
+    keepComments: false,
+    affiliationNewline: true,
     toc: false,
   },
   tex: {
@@ -675,12 +677,16 @@ function generateMarkdownAuthorBlock(config: BuildConfig): string {
   lines.push('');
 
   // Affiliation lines: ^1^ Department of ...
-  for (const [key, text] of Object.entries(config.affiliations)) {
+  const affiliationEntries = Object.entries(config.affiliations);
+  const useLineBreaks = config.docx.affiliationNewline !== false;
+  affiliationEntries.forEach(([key, text], idx) => {
     const num = keyToNum.get(key);
     if (num !== undefined) {
-      lines.push(`^${num}^ ${text}`);
+      const isLast = idx === affiliationEntries.length - 1;
+      const suffix = useLineBreaks && !isLast ? '\\' : '';
+      lines.push(`^${num}^ ${text}${suffix}`);
     }
-  }
+  });
 
   // Corresponding author footnote
   const corresponding = config.authors.find(a => typeof a !== 'string' && a.corresponding) as Author | undefined;

package/lib/wordcomments.ts

@@ -478,8 +478,31 @@ export async function injectCommentsAtMarkers(
       const startMarker = `${MARKER_START_PREFIX}${idx}${MARKER_SUFFIX}`;
       const endMarker = `${MARKER_END_PREFIX}${idx}${MARKER_SUFFIX}`;
 
-      const startPos = documentXml.indexOf(startMarker);
-      const endPos = documentXml.indexOf(endMarker, startPos + startMarker.length);
+      // Pandoc duplicates inline image alt-text into <wp:docPr descr="...">
+      // metadata attributes AND into the visible caption paragraph. A naive
+      // indexOf hits the metadata-attribute occurrence first, where there is
+      // no <w:t> element so dissectRun fails. Skip occurrences whose position
+      // is inside an XML tag (last unbalanced '<' before position).
+      // See: https://github.com/gcol33/docrev/issues/4
+      function findInTextContent(haystack: string, needle: string, fromIdx = 0): number {
+        let i = fromIdx;
+        while (true) {
+          const p = haystack.indexOf(needle, i);
+          if (p < 0) return -1;
+          const lastLt = haystack.lastIndexOf('<', p);
+          const lastGt = haystack.lastIndexOf('>', p);
+          if (lastLt > lastGt) {
+            i = p + 1;
+            continue;
+          }
+          return p;
+        }
+      }
+
+      const startPos = findInTextContent(documentXml, startMarker);
+      const endPos = startPos === -1
+        ? -1
+        : findInTextContent(documentXml, endMarker, startPos + startMarker.length);
 
       if (startPos === -1 || endPos === -1) continue;
 

package/mkdocs.yml

@@ -0,0 +1,64 @@
+site_name: docrev
+site_url: https://gillescolling.com/docrev
+site_description: CLI for writing documents in Markdown while collaborating with Word users.
+site_author: Gilles Colling
+repo_url: https://github.com/gcol33/docrev
+repo_name: gcol33/docrev
+
+theme:
+  name: material
+  palette:
+    - scheme: default
+      primary: custom
+      accent: custom
+      toggle:
+        icon: material/brightness-7
+        name: Switch to dark mode
+    - scheme: slate
+      primary: custom
+      accent: custom
+      toggle:
+        icon: material/brightness-4
+        name: Switch to light mode
+  font:
+    text: Roboto
+    code: Roboto Mono
+  features:
+    - navigation.tabs
+    - navigation.top
+    - navigation.instant
+    - search.highlight
+    - content.code.copy
+  icon:
+    repo: fontawesome/brands/github
+
+nav:
+  - Home: index.md
+  - Get Started: workflow.md
+  - Commands: commands.md
+  - Configuration: configuration.md
+  - Troubleshooting: troubleshooting.md
+
+markdown_extensions:
+  - pymdownx.highlight:
+      anchor_linenums: true
+  - pymdownx.superfences
+  - pymdownx.inlinehilite
+  - pymdownx.tabbed:
+      alternate_style: true
+  - admonition
+  - pymdownx.details
+  - attr_list
+  - md_in_html
+  - toc:
+      permalink: true
+
+extra_css:
+  - stylesheets/extra.css
+
+extra:
+  social:
+    - icon: fontawesome/brands/github
+      link: https://github.com/gcol33/docrev
+    - icon: fontawesome/brands/npm
+      link: https://www.npmjs.com/package/docrev

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docrev",
-  "version": "0.9.15",
+  "version": "0.9.17",
   "description": "Academic paper revision workflow: Word ↔ Markdown round-trips, DOI validation, reviewer comments",
   "type": "module",
   "types": "dist/lib/types.d.ts",

package/dev_notes/bug_repro_comment_parser.md

@@ -1,71 +0,0 @@
-# Bug repro — comment parser drops valid comments
-
-## Symptom
-
-A markdown file with 24 valid `{>>Author: text<<}` comments is shown by `rev comments file.md` as containing only 21. Three comments are silently dropped.
-
-## Reproducer
-
-`test.md`:
-```markdown
-# Test
-
-**Para 1.** Sentence one{>>Jonathan Lenoir: short comment<<}.
-
-**Para 2.** Sentence two{>>Jens-Christian Svenning: I'm quite skeptical about these listings of all the bad things alien species do, with any kind of proper benchmarking - you could arguably make similar lists of all the annoying or dangerous things native species do<<}.
-
-**Para 3.** Sentence three{>>Jens-Christian Svenning: see https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/1365-2745.14307<<}.
-```
-
-```bash
-rev comments test.md
-```
-
-**Expected:** 3 comments listed.
-**Actual:** 1 comment listed (Lenoir's short comment). Both Svenning comments are dropped.
-
-## Root cause — `lib/annotations.ts`
-
-### Bug A: hyphenated reviewer names (line 102)
-
-```ts
-const hasAuthorPrefix = /^[A-Za-z][A-Za-z\s]{0,20}:\s/.test(commentContent.trim());
-```
-
-The character class `[A-Za-z\s]` forbids hyphens, apostrophes, and accented characters. So:
-
-- `Jens-Christian Svenning:` — fails (hyphen at position 4)
-- `Camilla T Colding-Jørgensen:` — fails (hyphen + diacritic)
-- `Renata Ćušterevska:` — fails (diacritic at position 7)
-- Any name with `-`, `'`, or non-ASCII letters fails
-
-When `hasAuthorPrefix === false` AND content > `MAX_COMMENT_CONTENT_LENGTH = 200`, line 104 discards the comment. Any long comment from a hyphenated reviewer is silently dropped.
-
-### Bug B: any comment containing a URL <150 chars (line 95)
-
-```ts
-if (/https?:\/\/|www\./i.test(commentContent) && commentContent.length < 150) return true;
-```
-
-This filter assumes URLs in CriticMarkup blocks are markdown links wrapped in CriticMarkup syntax (a real false positive). But reviewers legitimately cite URLs/DOIs inside comments — that gets dropped too.
-
-`{>>Lenoir: see https://www.pnas.org/doi/10.1073/pnas.1608980113<<}` — 60 chars, contains URL → dropped, even though `Lenoir:` is a valid author prefix.
-
-## Suggested fix
-
-1. **Line 102 — broaden author-prefix regex:**
-   ```ts
-   const hasAuthorPrefix = /^[\p{L}][\p{L}\s\-'.]{0,30}:\s/u.test(commentContent.trim());
-   ```
-   Allows hyphens, apostrophes, periods, and Unicode letters. Length bumped to 30 (Camilla T Colding-Jørgensen is 27 chars).
-
-2. **Line 95 — only filter URLs when there's no author prefix:**
-   ```ts
-   const looksLikeAuthor = /^[\p{L}][\p{L}\s\-'.]{0,30}:\s/u.test(commentContent.trim());
-   if (!looksLikeAuthor && /https?:\/\/|www\./i.test(commentContent) && commentContent.length < 150) return true;
-   ```
-   A comment with a real `Author:` prefix should not be dropped just because it cites a URL.
-
-## Impact
-
-In `paper_hexgrids_2026/abstract.md`, three reviewer comments from Jens-Christian Svenning (one tone-related, two with cited URLs/DOIs) were silently dropped from `rev comments`, `rev next`, and presumably `rev build docx --dual` output. Other affected reviewers in this manuscript: Camilla T Colding-Jørgensen (long comments would drop), Renata Ćušterevska, Jean-Christian Svenning across all sections.

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.