docrev 0.11.3 → 0.12.0

package/lib/git.ts

@@ -1,326 +0,0 @@
-/**
- * Git integration utilities
- * Compare sections against git history
- */
-
-import { execSync } from 'child_process';
-import * as fs from 'fs';
-import * as path from 'path';
-import { diffWords } from 'diff';
-import type { FileChange, CommitInfo, ChangedFile, BlameEntry, AuthorStats, ContributorStats } from './types.js';
-
-/**
- * Check if current directory is a git repository
- */
-export function isGitRepo(): boolean {
-  try {
-    execSync('git rev-parse --is-inside-work-tree', { stdio: 'pipe' });
-    return true;
-  } catch {
-    return false;
-  }
-}
-
-/**
- * Get the current git branch
- */
-export function getCurrentBranch(): string | null {
-  try {
-    return execSync('git rev-parse --abbrev-ref HEAD', { stdio: 'pipe' })
-      .toString()
-      .trim();
-  } catch {
-    return null;
-  }
-}
-
-/**
- * Get the default branch (main or master)
- */
-export function getDefaultBranch(): string {
-  try {
-    // Try to get the remote default branch
-    const remote = execSync('git remote show origin', { stdio: 'pipe' })
-      .toString();
-    const match = remote.match(/HEAD branch:\s*(\S+)/);
-    if (match?.[1]) return match[1];
-  } catch {
-    // Fall through
-  }
-
-  // Check if main or master exists
-  try {
-    execSync('git rev-parse --verify main', { stdio: 'pipe' });
-    return 'main';
-  } catch {
-    try {
-      execSync('git rev-parse --verify master', { stdio: 'pipe' });
-      return 'master';
-    } catch {
-      return 'main'; // Default fallback
-    }
-  }
-}
-
-/**
- * Get file content from a specific git ref
- * @param filePath - Path to file
- * @param ref - Git reference (branch, tag, commit)
- */
-export function getFileAtRef(filePath: string, ref: string): string | null {
-  try {
-    return execSync(`git show ${ref}:${filePath}`, { stdio: 'pipe' }).toString();
-  } catch {
-    return null; // File doesn't exist at that ref
-  }
-}
-
-/**
- * Get list of changed files between refs
- * @param fromRef - Starting reference
- * @param toRef - Ending reference (default: HEAD)
- */
-export function getChangedFiles(fromRef: string, toRef: string = 'HEAD'): ChangedFile[] {
-  try {
-    const output = execSync(`git diff --name-status ${fromRef}..${toRef}`, { stdio: 'pipe' })
-      .toString()
-      .trim();
-
-    if (!output) return [];
-
-    return output.split('\n').map(line => {
-      const parts = line.split('\t');
-      const status = parts[0];
-      const file = parts[1] ?? '';
-      return {
-        file,
-        status: (status === 'A' ? 'added' : status === 'D' ? 'deleted' : 'modified') as 'added' | 'deleted' | 'modified',
-      };
-    });
-  } catch {
-    return [];
-  }
-}
-
-/**
- * Run git log with a given format and optional file path, parse pipe-delimited output
- */
-function runGitLog(
-  format: string,
-  limit: number,
-  fields: (keyof CommitInfo)[],
-  filePath?: string,
-): CommitInfo[] {
-  try {
-    const fileArg = filePath ? ` -- "${filePath}"` : '';
-    const output = execSync(
-      `git log --format="${format}" -n ${limit}${fileArg}`,
-      { stdio: 'pipe' }
-    ).toString().trim();
-
-    if (!output) return [];
-
-    return output.split('\n').map(line => {
-      const parts = line.split('|');
-      const entry: CommitInfo = { hash: '', date: '', author: '', message: '' };
-      for (let i = 0; i < fields.length; i++) {
-        entry[fields[i]] = parts[i] ?? '';
-      }
-      return entry;
-    });
-  } catch {
-    return [];
-  }
-}
-
-/**
- * Get commit history for a file
- * @param filePath - Path to file
- * @param limit - Maximum number of commits to return
- */
-export function getFileHistory(filePath: string, limit: number = 10): CommitInfo[] {
-  return runGitLog('%h|%ci|%s', limit, ['hash', 'date', 'message'], filePath);
-}
-
-/**
- * Compare file content between two refs
- * @param filePath - Path to file
- * @param fromRef - Starting reference
- * @param toRef - Ending reference (default: HEAD)
- */
-export function compareFileVersions(filePath: string, fromRef: string, toRef: string = 'HEAD'): FileChange {
-  const oldContent = getFileAtRef(filePath, fromRef) || '';
-  const newContent = toRef === 'HEAD'
-    ? fs.existsSync(filePath) ? fs.readFileSync(filePath, 'utf-8') : ''
-    : getFileAtRef(filePath, toRef) || '';
-
-  const diffs = diffWords(oldContent, newContent);
-
-  let added = 0;
-  let removed = 0;
-  const changes: Array<{ added?: boolean; removed?: boolean; value: string }> = [];
-
-  for (const part of diffs) {
-    if (part.added) {
-      added += part.value.split(/\s+/).filter(w => w).length;
-      changes.push({ added: true, value: part.value });
-    } else if (part.removed) {
-      removed += part.value.split(/\s+/).filter(w => w).length;
-      changes.push({ removed: true, value: part.value });
-    }
-  }
-
-  return { added, removed, changes };
-}
-
-/**
- * Get word count difference between refs
- * @param files - Array of file paths
- * @param fromRef - Starting reference
- * @param toRef - Ending reference (default: HEAD)
- */
-export function getWordCountDiff(
-  files: string[],
-  fromRef: string,
-  toRef: string = 'HEAD'
-): { total: { added: number; removed: number }; byFile: Record<string, { added: number; removed: number }> } {
-  let totalAdded = 0;
-  let totalRemoved = 0;
-  const byFile: Record<string, { added: number; removed: number }> = {};
-
-  for (const file of files) {
-    const { added, removed } = compareFileVersions(file, fromRef, toRef);
-    totalAdded += added;
-    totalRemoved += removed;
-    byFile[file] = { added, removed };
-  }
-
-  return {
-    total: { added: totalAdded, removed: totalRemoved },
-    byFile,
-  };
-}
-
-/**
- * Get recent commits
- * @param limit - Maximum number of commits to return
- */
-export function getRecentCommits(limit: number = 10): CommitInfo[] {
-  return runGitLog('%h|%ci|%an|%s', limit, ['hash', 'date', 'author', 'message']);
-}
-
-/**
- * Check if there are uncommitted changes
- */
-export function hasUncommittedChanges(): boolean {
-  try {
-    const output = execSync('git status --porcelain', { stdio: 'pipe' }).toString();
-    return output.trim().length > 0;
-  } catch {
-    return false;
-  }
-}
-
-/**
- * Get tags
- */
-export function getTags(): string[] {
-  try {
-    return execSync('git tag --sort=-creatordate', { stdio: 'pipe' })
-      .toString()
-      .trim()
-      .split('\n')
-      .filter(t => t);
-  } catch {
-    return [];
-  }
-}
-
-/**
- * Get blame information for a file
- * Returns author and commit info for each line
- * @param filePath - Path to file
- */
-export function getFileBlame(filePath: string): BlameEntry[] {
-  try {
-    const output = execSync(
-      `git blame --line-porcelain "${filePath}"`,
-      { stdio: 'pipe', maxBuffer: 10 * 1024 * 1024 }
-    ).toString();
-
-    const lines = output.split('\n');
-    const result: BlameEntry[] = [];
-    let current: Partial<BlameEntry> = {};
-    let lineNumber = 0;
-
-    for (const line of lines) {
-      if (/^[0-9a-f]{40}/.test(line)) {
-        // New blame entry: hash original-line final-line [count]
-        const parts = line.split(' ');
-        current.hash = parts[0]?.slice(0, 7) ?? '';
-        lineNumber = parseInt(parts[2] ?? '0', 10);
-      } else if (line.startsWith('author ')) {
-        current.author = line.slice(7);
-      } else if (line.startsWith('author-time ')) {
-        const timestamp = parseInt(line.slice(12), 10);
-        current.date = new Date(timestamp * 1000).toISOString().slice(0, 10);
-      } else if (line.startsWith('\t')) {
-        // Actual content line (prefixed with tab)
-        current.content = line.slice(1);
-        current.line = lineNumber;
-        result.push(current as BlameEntry);
-        current = {};
-      }
-    }
-
-    return result;
-  } catch {
-    return [];
-  }
-}
-
-/**
- * Get author statistics for a file
- * @param filePath - Path to file
- */
-export function getAuthorStats(filePath: string): Record<string, AuthorStats> {
-  const blame = getFileBlame(filePath);
-  if (blame.length === 0) return {};
-
-  const counts: Record<string, number> = {};
-  for (const entry of blame) {
-    counts[entry.author] = (counts[entry.author] || 0) + 1;
-  }
-
-  const total = blame.length;
-  const stats: Record<string, AuthorStats> = {};
-  for (const [author, lines] of Object.entries(counts)) {
-    stats[author] = {
-      lines,
-      percentage: Math.round((lines / total) * 100),
-    };
-  }
-
-  return stats;
-}
-
-/**
- * Get contributors across multiple files
- * @param files - Array of file paths
- */
-export function getContributors(files: string[]): Record<string, ContributorStats> {
-  const contributors: Record<string, ContributorStats> = {};
-
-  for (const file of files) {
-    const stats = getAuthorStats(file);
-    for (const [author, data] of Object.entries(stats)) {
-      if (!contributors[author]) {
-        contributors[author] = { lines: 0, files: 0 };
-      }
-      contributors[author].lines += data.lines;
-      contributors[author].files += 1;
-    }
-  }
-
-  return contributors;
-}

package/lib/grammar.ts

@@ -1,303 +0,0 @@
-/**
- * Grammar checker module with custom dictionary support
- *
- * Features:
- * - Common grammar/style issues detection
- * - Custom dictionary for project-specific terms
- * - Learn mode to add words to dictionary
- */
-
-import * as fs from 'fs';
-import * as path from 'path';
-
-// Default dictionary location
-const DEFAULT_DICT_NAME = '.rev-dictionary';
-
-interface GrammarRule {
-  id: string;
-  pattern: RegExp;
-  message: string;
-  severity: 'error' | 'warning' | 'info';
-  check?: (match: string) => boolean;
-}
-
-interface GrammarIssue {
-  rule: string;
-  message: string;
-  severity: 'error' | 'warning' | 'info';
-  line: number;
-  column: number;
-  match: string;
-  context: string;
-}
-
-interface GrammarSummary {
-  total: number;
-  errors: number;
-  warnings: number;
-  info: number;
-  byRule: Record<string, number>;
-}
-
-interface CheckGrammarOptions {
-  scientific?: boolean;
-  directory?: string;
-}
-
-/**
- * Common grammar/style rules
- */
-const GRAMMAR_RULES: GrammarRule[] = [
-  {
-    id: 'passive-voice',
-    pattern: /\b(is|are|was|were|be|been|being)\s+(being\s+)?\w+ed\b/gi,
-    message: 'Possible passive voice',
-    severity: 'info',
-  },
-  {
-    id: 'weasel-words',
-    pattern: /\b(very|really|quite|extremely|fairly|rather|somewhat|just)\b/gi,
-    message: 'Weasel word - consider removing or being more specific',
-    severity: 'warning',
-  },
-  {
-    id: 'weak-start',
-    pattern: /^\s*(There (is|are|was|were)|It is)\b/gmi,
-    message: 'Weak sentence start - consider restructuring',
-    severity: 'info',
-  },
-  {
-    id: 'duplicate-words',
-    pattern: /\b(\w+)\s+\1\b/gi,
-    message: 'Duplicate word',
-    severity: 'error',
-  },
-  {
-    id: 'split-infinitive',
-    pattern: /\bto\s+(\w+ly)\s+\w+\b/gi,
-    message: 'Split infinitive',
-    severity: 'info',
-  },
-  {
-    id: 'sentence-length',
-    pattern: /[^.!?]*[.!?]/g,
-    check: (match: string): boolean => {
-      const words = match.trim().split(/\s+/).length;
-      return words > 40;
-    },
-    message: 'Long sentence (>40 words) - consider breaking up',
-    severity: 'warning',
-  },
-  {
-    id: 'cliches',
-    pattern: /\b(at the end of the day|in terms of|it goes without saying|needless to say|as a matter of fact|first and foremost|last but not least)\b/gi,
-    message: 'Cliche - consider rephrasing',
-    severity: 'warning',
-  },
-  {
-    id: 'hedging',
-    pattern: /\b(seems to|appears to|tends to|might|may|could possibly|would seem)\b/gi,
-    message: 'Hedging language - be more direct if appropriate',
-    severity: 'info',
-  },
-  {
-    id: 'redundancy',
-    pattern: /\b(basic fundamentals|end result|free gift|future plans|past history|completely unique|absolutely essential|close proximity|each and every|first began|true fact|advance planning|final outcome)\b/gi,
-    message: 'Redundant phrase',
-    severity: 'warning',
-  },
-];
-
-/**
- * Scientific writing specific rules
- */
-const SCIENTIFIC_RULES: GrammarRule[] = [
-  {
-    id: 'first-person',
-    pattern: /\b(I|we|my|our)\b/gi,
-    message: 'First person pronoun - check if appropriate for your journal',
-    severity: 'info',
-  },
-  {
-    id: 'significant',
-    pattern: /\bsignificant(ly)?\b(?!\s+(P|p|α|difference|effect|increase|decrease|correlation))/gi,
-    message: '"Significant" without statistical context - clarify or use different word',
-    severity: 'warning',
-  },
-  {
-    id: 'prove',
-    pattern: /\b(prove[ds]?|proof)\b/gi,
-    message: 'Avoid "prove" in science - use "demonstrate", "show", "suggest"',
-    severity: 'warning',
-  },
-  {
-    id: 'obviously',
-    pattern: /\b(obviously|clearly|of course)\b/gi,
-    message: 'If obvious, no need to say so; if not obvious, this doesn\'t help',
-    severity: 'warning',
-  },
-];
-
-/**
- * Load custom dictionary from file
- */
-export function loadDictionary(directory: string = '.'): Set<string> {
-  const dictPath = path.join(directory, DEFAULT_DICT_NAME);
-  const words = new Set<string>();
-
-  if (fs.existsSync(dictPath)) {
-    const content = fs.readFileSync(dictPath, 'utf-8');
-    const lines = content.split('\n');
-
-    for (const line of lines) {
-      const word = line.trim().toLowerCase();
-      if (word && !word.startsWith('#')) {
-        words.add(word);
-      }
-    }
-  }
-
-  return words;
-}
-
-/**
- * Save custom dictionary to file
- */
-export function saveDictionary(words: Set<string>, directory: string = '.'): void {
-  const dictPath = path.join(directory, DEFAULT_DICT_NAME);
-
-  const header = `# Custom dictionary for docrev
-# Add one word per line
-# Lines starting with # are comments
-`;
-
-  const content = header + [...words].sort().join('\n') + '\n';
-  fs.writeFileSync(dictPath, content, 'utf-8');
-}
-
-/**
- * Add word to custom dictionary
- */
-export function addToDictionary(word: string, directory: string = '.'): boolean {
-  const words = loadDictionary(directory);
-  const normalizedWord = word.trim().toLowerCase();
-
-  if (words.has(normalizedWord)) {
-    return false;
-  }
-
-  words.add(normalizedWord);
-  saveDictionary(words, directory);
-  return true;
-}
-
-/**
- * Remove word from custom dictionary
- */
-export function removeFromDictionary(word: string, directory: string = '.'): boolean {
-  const words = loadDictionary(directory);
-  const normalizedWord = word.trim().toLowerCase();
-
-  if (!words.has(normalizedWord)) {
-    return false;
-  }
-
-  words.delete(normalizedWord);
-  saveDictionary(words, directory);
-  return true;
-}
-
-/**
- * Check text for grammar/style issues
- */
-export function checkGrammar(text: string, options: CheckGrammarOptions = {}): GrammarIssue[] {
-  const { scientific = true, directory = '.' } = options;
-  const customDict = loadDictionary(directory);
-  const issues: GrammarIssue[] = [];
-
-  // Get all rules
-  const rules = scientific ? [...GRAMMAR_RULES, ...SCIENTIFIC_RULES] : GRAMMAR_RULES;
-
-  // Split into lines for line number tracking
-  const lines = text.split('\n');
-
-  for (let lineNum = 0; lineNum < lines.length; lineNum++) {
-    const line = lines[lineNum];
-    if (!line) continue;
-
-    // Skip code blocks and YAML frontmatter
-    if (line.trim().startsWith('```') || line.trim().startsWith('---')) {
-      continue;
-    }
-
-    // Skip lines that are just markdown syntax
-    if (/^[#\-*>|]/.test(line.trim()) && line.trim().length < 5) {
-      continue;
-    }
-
-    for (const rule of rules) {
-      const pattern = new RegExp(rule.pattern.source, rule.pattern.flags);
-      let match;
-
-      while ((match = pattern.exec(line)) !== null) {
-        // Check if rule has additional check function
-        if (rule.check && !rule.check(match[0])) {
-          continue;
-        }
-
-        // Skip if word is in custom dictionary
-        const word = match[0].toLowerCase();
-        if (customDict.has(word)) {
-          continue;
-        }
-
-        issues.push({
-          rule: rule.id,
-          message: rule.message,
-          severity: rule.severity,
-          line: lineNum + 1,
-          column: match.index + 1,
-          match: match[0],
-          context: line.trim(),
-        });
-      }
-    }
-  }
-
-  return issues;
-}
-
-/**
- * Get grammar check summary
- */
-export function getGrammarSummary(issues: GrammarIssue[]): GrammarSummary {
-  const summary: GrammarSummary = {
-    total: issues.length,
-    errors: 0,
-    warnings: 0,
-    info: 0,
-    byRule: {},
-  };
-
-  for (const issue of issues) {
-    if (issue.severity === 'error') summary.errors++;
-    else if (issue.severity === 'warning') summary.warnings++;
-    else summary.info++;
-
-    summary.byRule[issue.rule] = (summary.byRule[issue.rule] || 0) + 1;
-  }
-
-  return summary;
-}
-
-/**
- * List available grammar rules
- */
-export function listRules(scientific: boolean = true): Array<{ id: string; message: string; severity: string }> {
-  const rules = scientific ? [...GRAMMAR_RULES, ...SCIENTIFIC_RULES] : GRAMMAR_RULES;
-  return rules.map(r => ({
-    id: r.id,
-    message: r.message,
-    severity: r.severity,
-  }));
-}