docrev 0.2.0

package/lib/sections.js

@@ -0,0 +1,345 @@
+/**
+ * Section handling - map between section .md files and combined documents
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+import * as yaml from 'js-yaml';
+
+/**
+ * @typedef {Object} SectionConfig
+ * @property {string} header - Primary header text to match
+ * @property {string[]} [aliases] - Alternative header texts
+ * @property {number} [order] - Sort order for building
+ */
+
+/**
+ * @typedef {Object<string, SectionConfig|string>} SectionsConfig
+ */
+
+/**
+ * Default section order (common academic paper structure)
+ */
+const DEFAULT_ORDER = [
+  'abstract',
+  'introduction',
+  'background',
+  'literature',
+  'theory',
+  'methods',
+  'materials',
+  'data',
+  'results',
+  'analysis',
+  'discussion',
+  'conclusion',
+  'references',
+  'appendix',
+  'supplementary',
+];
+
+/**
+ * Extract header from a markdown file
+ * @param {string} filePath
+ * @returns {string|null}
+ */
+export function extractHeader(filePath) {
+  if (!fs.existsSync(filePath)) return null;
+
+  const content = fs.readFileSync(filePath, 'utf-8');
+  const lines = content.split('\n');
+
+  for (const line of lines) {
+    const match = line.match(/^#\s+(.+)$/);
+    if (match) {
+      return match[1].trim();
+    }
+  }
+
+  return null;
+}
+
+/**
+ * Generate sections.yaml from existing .md files
+ * @param {string} directory
+ * @param {string[]} [excludePatterns]
+ * @returns {object}
+ */
+export function generateConfig(directory, excludePatterns = ['paper.md', 'README.md', 'CLAUDE.md']) {
+  const files = fs.readdirSync(directory).filter((f) => {
+    if (!f.endsWith('.md')) return false;
+    if (excludePatterns.some((p) => f.toLowerCase().includes(p.toLowerCase()))) return false;
+    return true;
+  });
+
+  const sections = {};
+
+  for (const file of files) {
+    const filePath = path.join(directory, file);
+    const header = extractHeader(filePath);
+    const baseName = path.basename(file, '.md').toLowerCase();
+
+    // Determine order based on common patterns
+    let order = DEFAULT_ORDER.findIndex((s) => baseName.includes(s));
+    if (order === -1) order = 999;
+
+    sections[file] = {
+      header: header || titleCase(baseName),
+      aliases: [],
+      order: order,
+    };
+  }
+
+  // Sort by order
+  const sorted = Object.entries(sections)
+    .sort((a, b) => a[1].order - b[1].order)
+    .reduce((acc, [k, v]) => {
+      acc[k] = v;
+      return acc;
+    }, {});
+
+  return {
+    version: 1,
+    description: 'Section configuration for rev import/split',
+    sections: sorted,
+  };
+}
+
+/**
+ * Convert string to title case
+ * @param {string} str
+ * @returns {string}
+ */
+function titleCase(str) {
+  return str
+    .split(/[-_\s]+/)
+    .map((word) => word.charAt(0).toUpperCase() + word.slice(1))
+    .join(' ');
+}
+
+/**
+ * Load sections config from yaml file
+ * @param {string} configPath
+ * @returns {object}
+ */
+export function loadConfig(configPath) {
+  const content = fs.readFileSync(configPath, 'utf-8');
+  const config = yaml.load(content);
+
+  // Normalize: convert string values to full config objects
+  const normalized = { ...config };
+  normalized.sections = {};
+
+  for (const [file, value] of Object.entries(config.sections || {})) {
+    if (typeof value === 'string') {
+      normalized.sections[file] = {
+        header: value,
+        aliases: [],
+      };
+    } else {
+      normalized.sections[file] = {
+        header: value.header,
+        aliases: value.aliases || [],
+        order: value.order,
+      };
+    }
+  }
+
+  return normalized;
+}
+
+/**
+ * Save sections config to yaml file
+ * @param {string} configPath
+ * @param {object} config
+ */
+export function saveConfig(configPath, config) {
+  const yamlStr = yaml.dump(config, {
+    indent: 2,
+    lineWidth: 100,
+    quotingType: '"',
+    forceQuotes: false,
+  });
+  fs.writeFileSync(configPath, yamlStr, 'utf-8');
+}
+
+/**
+ * Match a heading to a section file
+ * @param {string} heading - Heading text from Word
+ * @param {object} sections - Sections config
+ * @returns {{file: string, config: SectionConfig}|null}
+ */
+export function matchHeading(heading, sections) {
+  const normalizedHeading = heading.toLowerCase().trim();
+
+  for (const [file, config] of Object.entries(sections)) {
+    // Check primary header
+    if (config.header.toLowerCase().trim() === normalizedHeading) {
+      return { file, config };
+    }
+
+    // Check aliases
+    if (config.aliases) {
+      for (const alias of config.aliases) {
+        if (alias.toLowerCase().trim() === normalizedHeading) {
+          return { file, config };
+        }
+      }
+    }
+
+    // Fuzzy match: check if heading contains the key words
+    const headerWords = config.header.toLowerCase().split(/\s+/);
+    const headingWords = normalizedHeading.split(/\s+/);
+    const matchCount = headerWords.filter((w) => headingWords.includes(w)).length;
+    if (matchCount >= headerWords.length * 0.7) {
+      return { file, config };
+    }
+  }
+
+  return null;
+}
+
+/**
+ * Extract sections from Word document text
+ * @param {string} text - Extracted text from Word
+ * @param {object} sections - Sections config
+ * @returns {Array<{file: string, header: string, content: string, matched: boolean}>}
+ */
+export function extractSectionsFromText(text, sections) {
+  const result = [];
+
+  // Find all headings (lines that look like headers - typically short, at start of "paragraph")
+  const paragraphs = text.split(/\n\n+/);
+  let currentSection = null;
+  let currentContent = [];
+
+  for (const para of paragraphs) {
+    const trimmed = para.trim();
+
+    // Detect if this paragraph is a heading
+    // Heuristics: short (< 100 chars), no periods, matches a known section
+    const isLikelyHeading = trimmed.length < 100 && !trimmed.includes('.') && trimmed.length > 0;
+
+    let matchedSection = null;
+    if (isLikelyHeading) {
+      matchedSection = matchHeading(trimmed, sections);
+    }
+
+    if (matchedSection) {
+      // Save previous section
+      if (currentSection) {
+        result.push({
+          file: currentSection.file,
+          header: currentSection.header,
+          content: currentContent.join('\n\n'),
+          matched: true,
+        });
+      }
+
+      currentSection = {
+        file: matchedSection.file,
+        header: trimmed,
+      };
+      currentContent = [];
+    } else {
+      currentContent.push(para);
+    }
+  }
+
+  // Save last section
+  if (currentSection) {
+    result.push({
+      file: currentSection.file,
+      header: currentSection.header,
+      content: currentContent.join('\n\n'),
+      matched: true,
+    });
+  }
+
+  return result;
+}
+
+/**
+ * Parse annotated paper.md and split back to section files
+ * @param {string} paperContent - Content of annotated paper.md
+ * @param {object} sections - Sections config
+ * @returns {Map<string, string>} - Map of filename → content
+ */
+export function splitAnnotatedPaper(paperContent, sections) {
+  const result = new Map();
+
+  // Look for section markers: <!-- @section:filename.md -->
+  const markerPattern = /<!--\s*@section:(\S+\.md)\s*-->/g;
+  const markers = [...paperContent.matchAll(markerPattern)];
+
+  if (markers.length > 0) {
+    // Use markers
+    for (let i = 0; i < markers.length; i++) {
+      const marker = markers[i];
+      const file = marker[1];
+      const start = marker.index + marker[0].length;
+      const end = markers[i + 1]?.index || paperContent.length;
+
+      let content = paperContent.slice(start, end).trim();
+
+      // Remove trailing marker if present
+      content = content.replace(/<!--\s*@section:\S+\.md\s*-->$/, '').trim();
+
+      result.set(file, content);
+    }
+  } else {
+    // Fall back to header detection
+    const lines = paperContent.split('\n');
+    let currentFile = null;
+    let currentContent = [];
+
+    for (const line of lines) {
+      const headerMatch = line.match(/^#\s+(.+)$/);
+
+      if (headerMatch) {
+        // Save previous section
+        if (currentFile) {
+          result.set(currentFile, currentContent.join('\n').trim());
+        }
+
+        // Find matching section file
+        const heading = headerMatch[1].trim();
+        const match = matchHeading(heading, sections);
+
+        if (match) {
+          currentFile = match.file;
+          currentContent = [line];
+        } else {
+          // Unknown section - keep accumulating to previous
+          currentContent.push(line);
+        }
+      } else {
+        currentContent.push(line);
+      }
+    }
+
+    // Save last section
+    if (currentFile) {
+      result.set(currentFile, currentContent.join('\n').trim());
+    }
+  }
+
+  return result;
+}
+
+/**
+ * Get ordered list of section files from config
+ * @param {object} config
+ * @returns {string[]}
+ */
+export function getOrderedSections(config) {
+  const entries = Object.entries(config.sections || {});
+
+  return entries
+    .sort((a, b) => {
+      const orderA = a[1].order ?? 999;
+      const orderB = b[1].order ?? 999;
+      return orderA - orderB;
+    })
+    .map(([file]) => file);
+}

package/lib/templates.js

@@ -0,0 +1,305 @@
+/**
+ * Built-in templates for project scaffolding
+ *
+ * Used by `rev new` command to create new paper projects
+ */
+
+export const TEMPLATES = {
+  /**
+   * Standard academic paper structure
+   */
+  paper: {
+    name: 'Academic Paper',
+    description: 'Standard paper with introduction, methods, results, discussion',
+    files: {
+      'rev.yaml': `# Paper configuration
+title: "Your Paper Title"
+authors:
+  - name: First Author
+    affiliation: Institution
+    email: author@example.com
+
+# Section files in order
+sections:
+  - introduction.md
+  - methods.md
+  - results.md
+  - discussion.md
+
+# Bibliography (optional)
+bibliography: references.bib
+csl: null  # uses default CSL
+
+# Cross-reference settings
+crossref:
+  figureTitle: Figure
+  tableTitle: Table
+  figPrefix: [Fig., Figs.]
+  tblPrefix: [Table, Tables]
+  linkReferences: true
+
+# PDF output settings
+pdf:
+  documentclass: article
+  fontsize: 12pt
+  geometry: margin=1in
+  linestretch: 1.5
+  numbersections: false
+
+# Word output settings
+docx:
+  reference: null  # path to reference.docx template
+  keepComments: true
+`,
+      'introduction.md': `# Introduction
+
+Your introduction goes here. Use dynamic figure references like @fig:example.
+
+`,
+      'methods.md': `# Methods
+
+## Study Design
+
+Describe your methodology here.
+
+## Data Analysis
+
+Reference tables with @tbl:summary.
+
+`,
+      'results.md': `# Results
+
+Present your findings. See @fig:results for the main analysis.
+
+![Example figure caption](figures/placeholder.png){#fig:results}
+
+`,
+      'discussion.md': `# Discussion
+
+Interpret your results here.
+
+## Conclusions
+
+Summarize key findings.
+
+`,
+      'references.bib': `@article{example2024,
+  author = {Author, A. and Coauthor, B.},
+  title = {An Example Paper Title},
+  journal = {Journal Name},
+  year = {2024},
+  volume = {1},
+  pages = {1--10}
+}
+`,
+      '.gitignore': `# Build outputs
+*.pdf
+*.docx
+*.tex
+paper.md
+.paper-*.md
+
+# System
+.DS_Store
+`,
+    },
+    directories: ['figures'],
+  },
+
+  /**
+   * Minimal single-section document
+   */
+  minimal: {
+    name: 'Minimal',
+    description: 'Single document with basic config',
+    files: {
+      'rev.yaml': `title: "Document Title"
+authors: []
+sections:
+  - content.md
+`,
+      'content.md': `# Your Document
+
+Write your content here.
+
+`,
+    },
+    directories: [],
+  },
+
+  /**
+   * Thesis chapter structure
+   */
+  thesis: {
+    name: 'Thesis Chapter',
+    description: 'Thesis-style with abstract, sections, appendix',
+    files: {
+      'rev.yaml': `title: "Chapter Title"
+authors:
+  - name: Your Name
+    affiliation: University
+
+sections:
+  - abstract.md
+  - introduction.md
+  - literature.md
+  - methods.md
+  - results.md
+  - discussion.md
+  - conclusion.md
+  - appendix.md
+
+bibliography: references.bib
+
+pdf:
+  documentclass: report
+  fontsize: 11pt
+  geometry: "margin=1in"
+  linestretch: 2
+  numbersections: true
+`,
+      'abstract.md': `# Abstract
+
+Brief summary of the chapter (150-300 words).
+
+`,
+      'introduction.md': `# Introduction
+
+Background and research questions.
+
+`,
+      'literature.md': `# Literature Review
+
+Review of relevant prior work.
+
+`,
+      'methods.md': `# Materials and Methods
+
+Detailed methodology.
+
+`,
+      'results.md': `# Results
+
+Findings and analysis.
+
+`,
+      'discussion.md': `# Discussion
+
+Interpretation of results.
+
+`,
+      'conclusion.md': `# Conclusion
+
+Summary and implications.
+
+`,
+      'appendix.md': `# Appendix
+
+## Supplementary Materials
+
+Additional details here.
+
+`,
+      'references.bib': ``,
+      '.gitignore': `*.pdf
+*.docx
+*.tex
+paper.md
+.paper-*.md
+.DS_Store
+`,
+    },
+    directories: ['figures', 'tables'],
+  },
+
+  /**
+   * Review article structure
+   */
+  review: {
+    name: 'Review Article',
+    description: 'Literature review or synthesis paper',
+    files: {
+      'rev.yaml': `title: "Review Title"
+authors:
+  - name: Author Name
+    affiliation: Institution
+
+sections:
+  - introduction.md
+  - section1.md
+  - section2.md
+  - section3.md
+  - synthesis.md
+  - conclusion.md
+
+bibliography: references.bib
+
+crossref:
+  figureTitle: Figure
+  tableTitle: Table
+  figPrefix: [Fig., Figs.]
+  tblPrefix: [Table, Tables]
+`,
+      'introduction.md': `# Introduction
+
+Scope and objectives of the review.
+
+`,
+      'section1.md': `# Theme One
+
+First major theme or topic.
+
+`,
+      'section2.md': `# Theme Two
+
+Second major theme.
+
+`,
+      'section3.md': `# Theme Three
+
+Third major theme.
+
+`,
+      'synthesis.md': `# Synthesis
+
+Integration of themes and emerging patterns.
+
+`,
+      'conclusion.md': `# Conclusion and Future Directions
+
+Key takeaways and research gaps.
+
+`,
+      'references.bib': ``,
+      '.gitignore': `*.pdf
+*.docx
+*.tex
+paper.md
+.paper-*.md
+.DS_Store
+`,
+    },
+    directories: ['figures'],
+  },
+};
+
+/**
+ * Get template by name
+ * @param {string} name
+ * @returns {object|null}
+ */
+export function getTemplate(name) {
+  return TEMPLATES[name.toLowerCase()] || null;
+}
+
+/**
+ * List available templates
+ * @returns {Array<{id: string, name: string, description: string}>}
+ */
+export function listTemplates() {
+  return Object.entries(TEMPLATES).map(([id, template]) => ({
+    id,
+    name: template.name,
+    description: template.description,
+  }));
+}

package/package.json

@@ -0,0 +1,43 @@
+{
+  "name": "docrev",
+  "version": "0.2.0",
+  "description": "Academic paper revision workflow: Word ↔ Markdown round-trips, DOI validation, reviewer comments",
+  "type": "module",
+  "bin": {
+    "rev": "bin/rev.js"
+  },
+  "scripts": {
+    "build": "echo 'No build needed'",
+    "test": "node bin/rev.js --help"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/gcol33/rev.git"
+  },
+  "bugs": {
+    "url": "https://github.com/gcol33/rev/issues"
+  },
+  "homepage": "https://github.com/gcol33/rev#readme",
+  "keywords": [
+    "markdown",
+    "word",
+    "docx",
+    "track-changes",
+    "comments",
+    "academic",
+    "writing",
+    "pandoc",
+    "criticmarkup"
+  ],
+  "author": "Gilles Colling",
+  "license": "MIT",
+  "dependencies": {
+    "adm-zip": "^0.5.16",
+    "chalk": "^5.3.0",
+    "commander": "^12.0.0",
+    "diff": "^8.0.2",
+    "js-yaml": "^4.1.1",
+    "mammoth": "^1.6.0",
+    "xml2js": "^0.6.2"
+  }
+}