docrev 0.9.14 → 0.9.16

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}`);

package/dev_notes/stresstest_pstyle.ts

@@ -1,55 +0,0 @@
-// Inspect the document.xml paragraph styles to find true headings.
-import AdmZip from 'adm-zip';
-import * as fs from 'fs';
-
-const docx = 'C:/GillesC/tmp/docrev-stress/reviewed.docx';
-const zip = new AdmZip(docx);
-const xml = zip.getEntry('word/document.xml')!.getData().toString('utf8');
-
-// Build text-position map from <w:t> runs the same way extractCommentAnchors does
-const textNodePattern = /<w:t[^>]*>([^<]*)<\/w:t>/g;
-const textNodes: Array<{ xmlStart: number; xmlEnd: number; textStart: number; textEnd: number; text: string }> = [];
-let textPosition = 0;
-let m;
-function decode(s: string): string {
-  return s.replace(/&amp;/g, '&').replace(/&lt;/g, '<').replace(/&gt;/g, '>').replace(/&quot;/g, '"').replace(/&apos;/g, "'");
-}
-while ((m = textNodePattern.exec(xml)) !== null) {
-  const decoded = decode(m[1]);
-  textNodes.push({ xmlStart: m.index, xmlEnd: m.index + m[0].length, textStart: textPosition, textEnd: textPosition + decoded.length, text: decoded });
-  textPosition += decoded.length;
-}
-
-function xmlToText(xmlPos: number): number {
-  for (const n of textNodes) {
-    if (xmlPos >= n.xmlStart && xmlPos < n.xmlEnd) return n.textStart;
-    if (xmlPos < n.xmlStart) return n.textStart;
-  }
-  return textNodes.length ? textNodes[textNodes.length - 1].textEnd : 0;
-}
-
-// Now walk paragraphs; each <w:p ...>...</w:p>. Inside, find <w:pStyle w:val="..."/> if present, and concatenate text runs.
-const paraPattern = /<w:p\b[^>]*>([\s\S]*?)<\/w:p>/g;
-const headings: Array<{ style: string; text: string; xmlStart: number; textPos: number }> = [];
-let pm;
-while ((pm = paraPattern.exec(xml)) !== null) {
-  const inner = pm[1];
-  const styleMatch = inner.match(/<w:pStyle[^>]*w:val="([^"]+)"/);
-  if (!styleMatch) continue;
-  const style = styleMatch[1];
-  if (!/heading/i.test(style)) continue;
-  // Extract text from runs
-  const textInRange = /<w:t[^>]*>([^<]*)<\/w:t>/g;
-  let txt = '';
-  let tm;
-  while ((tm = textInRange.exec(inner)) !== null) txt += decode(tm[1]);
-  if (!txt.trim()) continue;
-  const xmlStart = pm.index;
-  const textPos = xmlToText(xmlStart);
-  headings.push({ style, text: txt.trim(), xmlStart, textPos });
-}
-
-console.log(`Found ${headings.length} heading paragraphs:`);
-for (const h of headings) {
-  console.log(`  [${h.style.padEnd(8)}] textPos=${String(h.textPos).padStart(6)} "${h.text.slice(0, 60)}"`);
-}

package/dev_notes/stresstest_section_debug.ts

@@ -1,23 +0,0 @@
-import { extractCommentAnchors } from '../lib/import.js';
-
-const docx = 'C:/GillesC/tmp/docrev-stress/reviewed.docx';
-const { fullDocText } = await extractCommentAnchors(docx);
-
-const keywords = ['Abstract', 'Introduction', 'Methods', 'Results', 'Discussion', 'Conclusion', 'References'];
-for (const kw of keywords) {
-  const lower = fullDocText.toLowerCase();
-  const needle = kw.toLowerCase();
-  const occ: Array<{ idx: number; ctx: string; afterChar: string }> = [];
-  let idx = 0;
-  while ((idx = lower.indexOf(needle, idx)) !== -1) {
-    const ctx = fullDocText.slice(Math.max(0, idx - 20), idx + needle.length + 20).replace(/\s+/g, ' ');
-    const afterChar = fullDocText.slice(idx + needle.length, idx + needle.length + 1);
-    occ.push({ idx, ctx, afterChar });
-    idx++;
-  }
-  console.log(`\n--- ${kw} (${occ.length} occurrences) ---`);
-  for (const o of occ.slice(0, 6)) {
-    console.log(`  @${o.idx} after="${o.afterChar}" ctx: ...${o.ctx}...`);
-  }
-  if (occ.length > 6) console.log(`  ... and ${occ.length - 6} more`);
-}

package/dev_notes/stresstest_split.ts

@@ -1,70 +0,0 @@
-import * as fs from 'fs';
-import * as path from 'path';
-
-const ROOT = 'C:/GillesC/tmp/docrev-stress/project';
-fs.mkdirSync(ROOT, { recursive: true });
-
-const full = fs.readFileSync('C:/GillesC/tmp/docrev-stress/full.md', 'utf-8');
-const lines = full.split(/\r?\n/);
-
-interface Section { file: string; header: string; lines: string[]; }
-
-const sections: Section[] = [];
-
-// Map H1 heading text to section file
-const headerToFile: Record<string, string> = {
-  'Abstract': 'abstract.md',
-  'Introduction': 'introduction.md',
-  'Methods': 'methods.md',
-  'Results': 'results.md',
-  'Discussion': 'discussion.md',
-  'Conclusion': 'conclusion.md',
-  'References': 'references.md',
-  'Supplementary Materials': 'supplement.md',
-};
-
-let current: Section | null = null;
-const preambleLines: string[] = [];
-
-for (const line of lines) {
-  const m = line.match(/^# (.+)$/);
-  if (m && headerToFile[m[1].trim()]) {
-    if (current) sections.push(current);
-    current = { file: headerToFile[m[1].trim()], header: m[1].trim(), lines: [line] };
-  } else if (current) {
-    current.lines.push(line);
-  } else {
-    preambleLines.push(line);
-  }
-}
-if (current) sections.push(current);
-
-// Write sections
-for (const s of sections) {
-  const out = path.join(ROOT, s.file);
-  fs.writeFileSync(out, s.lines.join('\n'), 'utf-8');
-  console.log(`wrote ${out} (${s.lines.length} lines)`);
-}
-
-// Write sections.yaml
-const yaml: string[] = ['version: 1', 'sections:'];
-for (const s of sections) {
-  yaml.push(`  ${s.file}:`);
-  yaml.push(`    header: "${s.header}"`);
-  yaml.push(`    aliases: []`);
-}
-fs.writeFileSync(path.join(ROOT, 'sections.yaml'), yaml.join('\n') + '\n', 'utf-8');
-console.log(`wrote sections.yaml`);
-
-// Minimal rev.yaml so commands that look for project root don't choke
-const revYaml = `title: "Stress Test"
-authors:
-  - name: Gilles Colling
-output:
-  docx: {}
-  pdf: {}
-`;
-fs.writeFileSync(path.join(ROOT, 'rev.yaml'), revYaml, 'utf-8');
-
-console.log();
-console.log(`section files: ${sections.length}`);

package/dev_notes/stresstest_trace.ts

@@ -1,19 +0,0 @@
-import { extractCommentAnchors } from '../lib/import.js';
-
-const docx = 'C:/GillesC/tmp/docrev-stress/reviewed.docx';
-const { fullDocText } = await extractCommentAnchors(docx);
-
-const needle = 'methods';
-const lower = fullDocText.toLowerCase();
-let idx = 0;
-const trace: Array<{idx:number, after:string, skipped:boolean}> = [];
-while ((idx = lower.indexOf(needle, idx)) !== -1 && trace.length < 10) {
-  const after = fullDocText.slice(idx + needle.length, idx + needle.length + 5);
-  const skip = after.startsWith(':') || after.startsWith(' :');
-  trace.push({ idx, after, skipped: skip });
-  if (!skip) break;
-  idx++;
-}
-for (const t of trace) console.log(`idx=${t.idx} after="${t.after}" skipped=${t.skipped}`);
-console.log();
-console.log(`first non-:-prefixed Methods idx = ${trace.find(t => !t.skipped)?.idx ?? -1}`);

package/dev_notes/stresstest_verify_no_overwrite.ts

@@ -1,40 +0,0 @@
-// Verify sync --comments-only didn't touch existing prose, only inserted comments.
-import * as fs from 'fs';
-import { stripCriticMarkup } from '../lib/anchor-match.js';
-
-const original = 'C:/GillesC/tmp/docrev-stress/project';
-const synced = 'C:/GillesC/tmp/docrev-stress/project-sync';
-const files = ['abstract.md', 'introduction.md', 'methods.md', 'results.md', 'discussion.md', 'conclusion.md', 'references.md', 'supplement.md'];
-
-let totalComments = 0;
-let mismatches = 0;
-for (const f of files) {
-  const orig = fs.readFileSync(`${original}/${f}`, 'utf-8');
-  const synd = fs.readFileSync(`${synced}/${f}`, 'utf-8');
-
-  // Count comments inserted
-  const commentMatches = synd.match(/\{>>.*?<<\}/gs) || [];
-  totalComments += commentMatches.length;
-
-  // The originals may already contain CriticMarkup (Word highlights -> [X]{.mark}),
-  // so strip both sides to compare just the underlying prose.
-  const synStripped = stripCriticMarkup(synd);
-  const origNorm = stripCriticMarkup(orig);
-
-  if (synStripped !== origNorm) {
-    // Find first difference
-    let i = 0;
-    while (i < origNorm.length && i < synStripped.length && origNorm[i] === synStripped[i]) i++;
-    const ctxOrig = origNorm.slice(Math.max(0, i - 30), i + 50).replace(/\n/g, '\\n');
-    const ctxSyn = synStripped.slice(Math.max(0, i - 30), i + 50).replace(/\n/g, '\\n');
-    console.log(`✗ ${f}: prose differs at byte ${i} (lengths orig=${origNorm.length} stripped=${synStripped.length})`);
-    console.log(`    orig: ${ctxOrig}`);
-    console.log(`    syn:  ${ctxSyn}`);
-    mismatches++;
-  } else {
-    console.log(`✓ ${f}: prose preserved (${commentMatches.length} comments inserted)`);
-  }
-}
-console.log();
-console.log(`total comments inserted: ${totalComments}`);
-console.log(`prose mismatches:        ${mismatches}/${files.length}`);