confluence-exporter 1.0.0

package/dist/types.d.ts

@@ -0,0 +1,167 @@
+/**
+ * Minimal type definitions for Confluence export
+ */
+export interface ConfluenceConfig {
+    baseUrl: string;
+    username: string;
+    password: string;
+    spaceKey: string;
+    outputDir: string;
+    pageId?: string;
+    pageSize?: number;
+    limit?: number;
+    clear?: boolean;
+    force?: boolean;
+    debug?: boolean;
+    parallel?: number;
+}
+export interface Page {
+    id: string;
+    title: string;
+    body: string;
+    version?: number;
+    parentId?: string;
+    modifiedDate?: string;
+}
+export interface User {
+    userKey: string;
+    username: string;
+    displayName: string;
+    email?: string;
+}
+export interface PaginatedResponse<T> {
+    results: T[];
+    start: number;
+    limit: number;
+    size: number;
+    _links?: {
+        next?: string;
+    };
+}
+export interface PageResponse {
+    id: string;
+    title: string;
+    body?: {
+        storage?: {
+            value: string;
+        };
+    };
+    version?: {
+        number: number;
+        when?: string;
+    };
+    ancestors?: Array<{
+        id: string;
+    }>;
+    history?: {
+        lastUpdated?: {
+            when?: string;
+        };
+    };
+}
+export interface RawPage {
+    id: string;
+    title: string;
+    body?: {
+        storage?: {
+            value: string;
+        };
+    };
+    version?: {
+        number: number;
+        when?: string;
+    };
+    ancestors?: Array<{
+        id: string;
+    }>;
+    history?: {
+        lastUpdated?: {
+            when?: string;
+        };
+    };
+}
+export interface ListPagesResponse {
+    results: RawPage[];
+    start: number;
+    limit: number;
+    size: number;
+    _links?: {
+        next?: string;
+    };
+}
+export interface ChildPageResponse {
+    id: string;
+    title: string;
+    version?: {
+        number: number;
+    };
+}
+export interface ChildPagesResponse {
+    results: ChildPageResponse[];
+}
+export interface AttachmentResult {
+    id: string;
+    title: string;
+    _links: {
+        download: string;
+    };
+}
+export interface AttachmentResponse {
+    results: AttachmentResult[];
+}
+export interface PageMetadata {
+    id: string;
+    title: string;
+    version?: number;
+    parentId?: string;
+    modifiedDate?: string;
+}
+export interface PageIndexEntry {
+    id: string;
+    title: string;
+    version?: number;
+    parentId?: string;
+    modifiedDate?: string;
+    indexedDate: string;
+    pageNumber: number;
+    downloadedVersion?: number;
+    downloadedAt?: string;
+    queueReason?: 'new' | 'updated';
+}
+export interface PageIndex {
+    spaceKey: string;
+    exportDate: string;
+    totalPages: number;
+    pages: PageIndexEntry[];
+}
+export interface PageTreeNode {
+    id: string;
+    title: string;
+    version?: number;
+    parentId?: string;
+    modifiedDate?: string;
+    children?: PageTreeNode[];
+}
+export interface MarkdownResult {
+    content: string;
+    frontMatter: {
+        title: string;
+        id: string;
+        version?: number;
+        parentId?: string;
+    };
+    images: Array<{
+        filename: string;
+        data: Buffer;
+    }>;
+}
+/**
+ * Metadata sidecar file for tracking download state
+ * Stored as .meta.json alongside each .html file
+ */
+export interface PageMeta {
+    pageId: string;
+    version: number;
+    modifiedDate: string;
+    downloadedAt: string;
+}

package/dist/types.js

@@ -0,0 +1,5 @@
+/**
+ * Minimal type definitions for Confluence export
+ */
+export {};
+//# sourceMappingURL=types.js.map

package/dist/types.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA;;GAEG"}

package/dist/utils.d.ts

@@ -0,0 +1,56 @@
+import type { ConfluenceConfig, PageIndexEntry } from './types.js';
+/**
+ * Utility functions used across the application
+ */
+/**
+ * Convert text to safe filename/slug
+ *
+ * @param text - Text to slugify
+ * @returns Slugified text (lowercase, hyphens, no special chars)
+ *
+ * @example
+ * slugify("My Page Title!") // "my-page-title"
+ */
+export declare function slugify(text: string): string;
+/**
+ * Attempt to reverse slugification (best effort)
+ * Converts hyphens to spaces and capitalizes first letter of each word
+ *
+ * @param slug - Slugified text to convert back
+ * @returns Title-cased text with spaces
+ *
+ * @example
+ * unslugify("my-page-title") // "My Page Title"
+ */
+export declare function unslugify(slug: string): string;
+export declare const pageFilename: (item: PageIndexEntry, ext?: string) => string;
+export declare const pagePath: (id: string, config: ConfluenceConfig) => string;
+/**
+ * Read a specific entry from _index.yaml
+ */
+export declare function readIndexEntry(indexPath: string, pageId: string): PageIndexEntry | null;
+/**
+ * Update a specific entry in _index.yaml
+ */
+export declare function updateIndexEntry(indexPath: string, pageId: string, updates: Partial<PageIndexEntry>): boolean;
+/**
+ * Find existing HTML file for a page by ID
+ * Searches recursively in the output directory for {pageId}-*.html pattern
+ *
+ * @param outputDir - Root directory to search
+ * @param pageId - Page ID to find
+ * @returns Path to HTML file or null if not found
+ */
+export declare function findExistingFile(outputDir: string, pageId: string): string | null;
+/**
+ * Check if a page needs to be downloaded based on version comparison
+ * Uses index entry download tracking fields
+ *
+ * @param indexEntry - Page entry from index with current version
+ * @returns Object with needsDownload boolean and reason
+ */
+export declare function checkPageStatus(indexEntry: PageIndexEntry): {
+    needsDownload: boolean;
+    reason: 'new' | 'updated' | 'up-to-date';
+    details?: string;
+};

package/dist/utils.js

@@ -0,0 +1,178 @@
+import { parse, stringify } from 'yaml';
+import { readFileSync, existsSync, writeFileSync, readdirSync } from 'fs';
+import { join } from 'path';
+/**
+ * Utility functions used across the application
+ */
+/**
+ * Convert text to safe filename/slug
+ *
+ * @param text - Text to slugify
+ * @returns Slugified text (lowercase, hyphens, no special chars)
+ *
+ * @example
+ * slugify("My Page Title!") // "my-page-title"
+ */
+export function slugify(text) {
+    return text
+        .toLowerCase()
+        .replace(/[^\w\s-]/g, '') // Remove special chars
+        .replace(/\s+/g, '-') // Replace spaces with hyphens
+        .replace(/-+/g, '-') // Replace multiple hyphens with single
+        .trim();
+}
+/**
+ * Attempt to reverse slugification (best effort)
+ * Converts hyphens to spaces and capitalizes first letter of each word
+ *
+ * @param slug - Slugified text to convert back
+ * @returns Title-cased text with spaces
+ *
+ * @example
+ * unslugify("my-page-title") // "My Page Title"
+ */
+export function unslugify(slug) {
+    return slug
+        .replace(/-/g, ' ') // Replace hyphens with spaces
+        .replace(/\b\w/g, c => c.toUpperCase()); // Capitalize first letter of each word
+}
+export const pageFilename = (item, ext = '.md') => {
+    const slug = slugify(item.title);
+    return `${item.id}-${slug}${ext}`;
+};
+export const pagePath = (id, config) => {
+    const indexFile = join(config.outputDir, '_index.yaml');
+    const indexContent = readFileSync(indexFile, 'utf-8');
+    const index = parse(indexContent);
+    const findParents = (id, path) => {
+        const entry = index.find(e => e.id === id);
+        if (!entry)
+            return [];
+        path.unshift(pageFilename(entry, ''));
+        if (entry.parentId) {
+            return findParents(entry.parentId, path);
+        }
+        return path;
+    };
+    const item = index.find(e => e.id === id);
+    if (!item) {
+        throw new Error(`Page with ID ${id} not found in index`);
+    }
+    const parents = item.parentId ? findParents(item.parentId, []) : [];
+    return join(config.outputDir, config.spaceKey, ...parents, pageFilename(item, '.html'));
+};
+// ============================================================================
+// Page Metadata Utilities (Index-based)
+// ============================================================================
+/**
+ * Read a specific entry from _index.yaml
+ */
+export function readIndexEntry(indexPath, pageId) {
+    if (!existsSync(indexPath))
+        return null;
+    try {
+        const content = readFileSync(indexPath, 'utf-8');
+        const index = parse(content);
+        return index.find(entry => entry.id === pageId) || null;
+    }
+    catch {
+        return null;
+    }
+}
+/**
+ * Update a specific entry in _index.yaml
+ */
+export function updateIndexEntry(indexPath, pageId, updates) {
+    if (!existsSync(indexPath))
+        return false;
+    try {
+        const content = readFileSync(indexPath, 'utf-8');
+        const index = parse(content);
+        const entryIndex = index.findIndex(entry => entry.id === pageId);
+        if (entryIndex === -1)
+            return false;
+        // Update the entry
+        index[entryIndex] = { ...index[entryIndex], ...updates };
+        // Write back to file
+        const yamlContent = stringify(index, {
+            indent: 2,
+            lineWidth: 0
+        });
+        writeFileSync(indexPath, yamlContent, 'utf-8');
+        return true;
+    }
+    catch {
+        return false;
+    }
+}
+/**
+ * Find existing HTML file for a page by ID
+ * Searches recursively in the output directory for {pageId}-*.html pattern
+ *
+ * @param outputDir - Root directory to search
+ * @param pageId - Page ID to find
+ * @returns Path to HTML file or null if not found
+ */
+export function findExistingFile(outputDir, pageId) {
+    const pattern = new RegExp(`^${pageId}-.*\\.html$`);
+    function searchDir(dir) {
+        if (!existsSync(dir))
+            return null;
+        try {
+            const entries = readdirSync(dir, { withFileTypes: true });
+            for (const entry of entries) {
+                const fullPath = join(dir, entry.name);
+                if (entry.isFile() && pattern.test(entry.name)) {
+                    return fullPath;
+                }
+                if (entry.isDirectory() && !entry.name.startsWith('_') && entry.name !== 'images') {
+                    const found = searchDir(fullPath);
+                    if (found)
+                        return found;
+                }
+            }
+        }
+        catch {
+            // Ignore permission errors, etc.
+        }
+        return null;
+    }
+    return searchDir(outputDir);
+}
+/**
+ * Check if a page needs to be downloaded based on version comparison
+ * Uses index entry download tracking fields
+ *
+ * @param indexEntry - Page entry from index with current version
+ * @returns Object with needsDownload boolean and reason
+ */
+export function checkPageStatus(indexEntry) {
+    const downloadedVersion = indexEntry.downloadedVersion ?? 0;
+    const currentVersion = indexEntry.version ?? 0;
+    // If never downloaded, it's new
+    if (indexEntry.downloadedAt === undefined) {
+        return { needsDownload: true, reason: 'new' };
+    }
+    // Compare versions (primary check)
+    if (currentVersion > downloadedVersion) {
+        return {
+            needsDownload: true,
+            reason: 'updated',
+            details: `v${downloadedVersion} → v${currentVersion}`
+        };
+    }
+    // If versions match but downloadedVersion is 0 (fallback), compare dates
+    if (downloadedVersion === 0 && indexEntry.modifiedDate && indexEntry.downloadedAt) {
+        const currentDate = new Date(indexEntry.modifiedDate);
+        const downloadedDate = new Date(indexEntry.downloadedAt);
+        if (currentDate > downloadedDate) {
+            return {
+                needsDownload: true,
+                reason: 'updated',
+                details: `modified after download`
+            };
+        }
+    }
+    return { needsDownload: false, reason: 'up-to-date' };
+}
+//# sourceMappingURL=utils.js.map

package/dist/utils.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"utils.js","sourceRoot":"","sources":["../src/utils.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,MAAM,CAAC;AACxC,OAAW,EAAE,YAAY,EAAE,UAAU,EAAE,aAAa,EAAE,WAAW,EAAY,MAAM,IAAI,CAAC;AACxF,OAAO,EAAE,IAAI,EAAqB,MAAM,MAAM,CAAC;AAG/C;;GAEG;AAEH;;;;;;;;GAQG;AACH,MAAM,UAAU,OAAO,CAAC,IAAY;IAClC,OAAO,IAAI;SACR,WAAW,EAAE;SACb,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC,uBAAuB;SAChD,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAK,8BAA8B;SACvD,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAM,uCAAuC;SAChE,IAAI,EAAE,CAAC;AACZ,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,SAAS,CAAC,IAAY;IACpC,OAAO,IAAI;SACR,OAAO,CAAC,IAAI,EAAE,GAAG,CAAC,CAAW,8BAA8B;SAC3D,OAAO,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,uCAAuC;AACpF,CAAC;AAED,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,IAAoB,EAAE,GAAG,GAAC,KAAK,EAAE,EAAE;IAC9D,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACjC,OAAO,GAAG,IAAI,CAAC,EAAE,IAAI,IAAI,GAAG,GAAG,EAAE,CAAC;AACpC,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,QAAQ,GAAG,CAAC,EAAU,EAAE,MAAwB,EAAE,EAAE;IAC/D,MAAM,SAAS,GAAG,IAAI,CAAC,MAAM,CAAC,SAAS,EAAE,aAAa,CAAC,CAAC;IACxD,MAAM,YAAY,GAAG,YAAY,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;IACtD,MAAM,KAAK,GAAG,KAAK,CAAC,YAAY,CAAqB,CAAC;IAEtD,MAAM,WAAW,GAAG,CAAC,EAAU,EAAE,IAAc,EAAY,EAAE;QAC3D,MAAM,KAAK,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;QAC3C,IAAI,CAAC,KAAK;YAAE,OAAO,EAAE,CAAC;QACtB,IAAI,CAAC,OAAO,CAAC,YAAY,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,CAAC;QACtC,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;YACnB,OAAO,WAAW,CAAC,KAAK,CAAC,QAAQ,EAAE,IAAI,CAAC,CAAC;QAC3C,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC,CAAC;IACF,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;IAC1C,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,gBAAgB,EAAE,qBAAqB,CAAC,CAAC;IAC3D,CAAC;IACD,MAAM,OAAO,GAAG,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IACpE,OAAO,IAAI,CAAC,MAAM,CAAC,SAAS,EAAE,MAAM,CAAC,QAAQ,EAAE,GAAG,OAAO,EAAE,YAAY,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,CAAC;AAC1F,CAAC,CAAA;AAED,+EAA+E;AAC/E,wCAAwC;AACxC,+EAA+E;AAE/E;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,SAAiB,EAAE,MAAc;IAC9D,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;QAAE,OAAO,IAAI,CAAC;IAExC,IAAI,CAAC;QACH,MAAM,OAAO,GAAG,YAAY,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QACjD,MAAM,KAAK,GAAqB,KAAK,CAAC,OAAO,CAAC,CAAC;QAC/C,OAAO,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC;IAC1D,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,IAAI,CAAC;IACd,CAAC;AACH,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,gBAAgB,CAC9B,SAAiB,EACjB,MAAc,EACd,OAAgC;IAEhC,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;QAAE,OAAO,KAAK,CAAC;IAEzC,IAAI,CAAC;QACH,MAAM,OAAO,GAAG,YAAY,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QACjD,MAAM,KAAK,GAAqB,KAAK,CAAC,OAAO,CAAC,CAAC;QAE/C,MAAM,UAAU,GAAG,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC,KAAK,CAAC,EAAE,KAAK,MAAM,CAAC,CAAC;QACjE,IAAI,UAAU,KAAK,CAAC,CAAC;YAAE,OAAO,KAAK,CAAC;QAEpC,mBAAmB;QACnB,KAAK,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,KAAK,CAAC,UAAU,CAAC,EAAE,GAAG,OAAO,EAAE,CAAC;QAEzD,qBAAqB;QACrB,MAAM,WAAW,GAAG,SAAS,CAAC,KAAK,EAAE;YACnC,MAAM,EAAE,CAAC;YACT,SAAS,EAAE,CAAC;SACb,CAAC,CAAC;QACH,aAAa,CAAC,SAAS,EAAE,WAAW,EAAE,OAAO,CAAC,CAAC;QAE/C,OAAO,IAAI,CAAC;IACd,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,KAAK,CAAC;IACf,CAAC;AACH,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,gBAAgB,CAAC,SAAiB,EAAE,MAAc;IAChE,MAAM,OAAO,GAAG,IAAI,MAAM,CAAC,IAAI,MAAM,aAAa,CAAC,CAAC;IAEpD,SAAS,SAAS,CAAC,GAAW;QAC5B,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,OAAO,IAAI,CAAC;QAElC,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,WAAW,CAAC,GAAG,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,CAAC;YAE1D,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;gBAC5B,MAAM,QAAQ,GAAG,IAAI,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;gBAEvC,IAAI,KAAK,CAAC,MAAM,EAAE,IAAI,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC/C,OAAO,QAAQ,CAAC;gBAClB,CAAC;gBAED,IAAI,KAAK,CAAC,WAAW,EAAE,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,KAAK,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;oBAClF,MAAM,KAAK,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAC;oBAClC,IAAI,KAAK;wBAAE,OAAO,KAAK,CAAC;gBAC1B,CAAC;YACH,CAAC;QACH,CAAC;QAAC,MAAM,CAAC;YACP,iCAAiC;QACnC,CAAC;QAED,OAAO,IAAI,CAAC;IACd,CAAC;IAED,OAAO,SAAS,CAAC,SAAS,CAAC,CAAC;AAC9B,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,eAAe,CAC7B,UAA0B;IAE1B,MAAM,iBAAiB,GAAG,UAAU,CAAC,iBAAiB,IAAI,CAAC,CAAC;IAC5D,MAAM,cAAc,GAAG,UAAU,CAAC,OAAO,IAAI,CAAC,CAAC;IAE/C,gCAAgC;IAChC,IAAI,UAAU,CAAC,YAAY,KAAK,SAAS,EAAE,CAAC;QAC1C,OAAO,EAAE,aAAa,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;IAChD,CAAC;IAED,mCAAmC;IACnC,IAAI,cAAc,GAAG,iBAAiB,EAAE,CAAC;QACvC,OAAO;YACL,aAAa,EAAE,IAAI;YACnB,MAAM,EAAE,SAAS;YACjB,OAAO,EAAE,IAAI,iBAAiB,OAAO,cAAc,EAAE;SACtD,CAAC;IACJ,CAAC;IAED,yEAAyE;IACzE,IAAI,iBAAiB,KAAK,CAAC,IAAI,UAAU,CAAC,YAAY,IAAI,UAAU,CAAC,YAAY,EAAE,CAAC;QAClF,MAAM,WAAW,GAAG,IAAI,IAAI,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC;QACtD,MAAM,cAAc,GAAG,IAAI,IAAI,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC;QAEzD,IAAI,WAAW,GAAG,cAAc,EAAE,CAAC;YACjC,OAAO;gBACL,aAAa,EAAE,IAAI;gBACnB,MAAM,EAAE,SAAS;gBACjB,OAAO,EAAE,yBAAyB;aACnC,CAAC;QACJ,CAAC;IACH,CAAC;IAED,OAAO,EAAE,aAAa,EAAE,KAAK,EAAE,MAAM,EAAE,YAAY,EAAE,CAAC;AACxD,CAAC"}

package/eslint.config.js

@@ -0,0 +1,29 @@
+import js from '@eslint/js';
+import tseslint from 'typescript-eslint';
+
+export default [
+  { ignores: ['dist/**', 'node_modules/**', '**/*.cjs'] },
+  js.configs.recommended,
+  ...tseslint.configs.recommended,
+  {
+    files: ['**/*.ts'],
+    languageOptions: {
+      parser: tseslint.parser,
+      parserOptions: { sourceType: 'module', ecmaVersion: 'latest' }
+    },
+    rules: {
+      'no-unused-vars': 'off',
+      '@typescript-eslint/no-unused-vars': ['warn', { argsIgnorePattern: '^_', varsIgnorePattern: '^_' }],
+      'complexity': ['warn', 10],
+      'prefer-const': 'warn'
+    }
+  },
+  {
+    files: ['src/transform/cleanupRules/**/*.ts', 'src/services/markdownCleanupService.ts'],
+    rules: {
+      // Special rules for cleanup modules
+      'complexity': ['error', 8], // Stricter complexity for cleanup rules
+      '@typescript-eslint/explicit-function-return-type': 'warn'
+    }
+  }
+];

package/jest.config.cjs

@@ -0,0 +1,25 @@
+/** @type {import('jest').Config} */
+module.exports = {
+  preset: 'ts-jest/presets/default-esm',
+  testEnvironment: 'node',
+  roots: ['<rootDir>/tests'],
+  testMatch: ['**/*.test.ts'],
+  extensionsToTreatAsEsm: ['.ts'],
+  moduleNameMapper: {
+    '^(\\.{1,2}/.*)\\.js$': '$1',
+  },
+  transform: {
+    '^.+\\.ts$': ['ts-jest', {
+      useESM: true,
+      tsconfig: {
+        module: 'ESNext',
+        moduleResolution: 'node',
+      },
+    }],
+  },
+  moduleFileExtensions: ['ts', 'js', 'json'],
+  collectCoverageFrom: ['src/**/*.{ts,js}', '!src/**/*.test.ts'],
+  coverageDirectory: 'coverage',
+  testPathIgnorePatterns: ['/node_modules/', '/dist/'],
+  verbose: true,
+};

package/migrate-meta.js

@@ -0,0 +1,132 @@
+#!/usr/bin/env node
+/**
+ * Migration script: Move .meta.json data into _index.yaml
+ *
+ * This script reads all .meta.json files in the output directory
+ * and updates the corresponding entries in _index.yaml with
+ * downloadedVersion and downloadedAt fields.
+ *
+ * Usage: node migrate-meta.js <outputDir>
+ */
+
+import { readFileSync, writeFileSync, existsSync, readdirSync, statSync, unlinkSync } from 'fs';
+import { join, dirname, basename, extname } from 'path';
+import { parse, stringify } from 'yaml';
+
+function migrateMetaToIndex(outputDir) {
+  const indexPath = join(outputDir, '_index.yaml');
+
+  if (!existsSync(indexPath)) {
+    console.error(`❌ _index.yaml not found in ${outputDir}`);
+    process.exit(1);
+  }
+
+  console.log(`📖 Reading _index.yaml from ${indexPath}`);
+  const indexContent = readFileSync(indexPath, 'utf-8');
+  const index = parse(indexContent);
+
+  console.log(`📊 Found ${index.length} entries in index`);
+
+  let migrated = 0;
+  let skipped = 0;
+  const metaFiles = [];
+
+  // First pass: collect all .meta.json files
+  function collectMetaFiles(dir) {
+    if (!existsSync(dir)) return;
+
+    try {
+      const entries = readdirSync(dir, { withFileTypes: true });
+
+      for (const entry of entries) {
+        const fullPath = join(dir, entry.name);
+
+        if (entry.isDirectory() && !entry.name.startsWith('_') && entry.name !== 'images') {
+          collectMetaFiles(fullPath);
+        } else if (entry.isFile() && entry.name.endsWith('.meta.json')) {
+          metaFiles.push(fullPath);
+        }
+      }
+    } catch (error) {
+      console.warn(`⚠️  Could not read directory ${dir}:`, error);
+    }
+  }
+
+  function migrateMetaFile(metaPath) {
+    try {
+      const metaContent = readFileSync(metaPath, 'utf-8');
+      const meta = JSON.parse(metaContent);
+
+      // Find corresponding entry in index
+      const indexEntry = index.find(entry => entry.id === meta.pageId);
+      if (!indexEntry) {
+        console.log(`⚠️  No index entry found for page ${meta.pageId}, skipping`);
+        skipped++;
+        return;
+      }
+
+      // Update index entry with download metadata
+      indexEntry.downloadedVersion = meta.version;
+      indexEntry.downloadedAt = meta.downloadedAt;
+
+      console.log(`✅ Migrated ${meta.pageId} (${indexEntry.title}): v${meta.version} at ${meta.downloadedAt}`);
+
+      // Remove the .meta.json file
+      unlinkSync(metaPath);
+      migrated++;
+    } catch (error) {
+      console.error(`❌ Failed to migrate ${metaPath}:`, error);
+    }
+  }
+
+  function writeIndex() {
+    const header = `# Confluence Page Index
+# Migrated download metadata from .meta.json files
+# Created: ${new Date().toISOString()}
+
+`;
+    const yamlContent = stringify(index, {
+      indent: 2,
+      lineWidth: 0
+    });
+
+    writeFileSync(indexPath, header + yamlContent, 'utf-8');
+  }
+
+  console.log(`\n🔍 Scanning for .meta.json files in ${outputDir}...`);
+  collectMetaFiles(outputDir);
+
+  if (metaFiles.length === 0) {
+    console.log(`ℹ️  No .meta.json files found to migrate`);
+    return;
+  }
+
+  console.log(`📋 Found ${metaFiles.length} .meta.json files to migrate`);
+
+  // Process in batches of 100
+  const batchSize = 100;
+  for (let i = 0; i < metaFiles.length; i += batchSize) {
+    const batch = metaFiles.slice(i, i + batchSize);
+    console.log(`\n🔄 Processing batch ${Math.floor(i / batchSize) + 1}/${Math.ceil(metaFiles.length / batchSize)} (${batch.length} files)...`);
+
+    for (const metaPath of batch) {
+      migrateMetaFile(metaPath);
+    }
+
+    console.log(`💾 Writing updated _index.yaml after batch...`);
+    writeIndex();
+    console.log(`✅ Batch complete: ${migrated} total migrated so far`);
+  }
+
+  console.log(`\n✅ Migration complete: ${migrated} entries updated, ${skipped} skipped`);
+}
+const outputDir = process.argv[2] || './output';
+
+if (!outputDir) {
+  console.error('Usage: node migrate-meta.js <outputDir>');
+  process.exit(1);
+}
+
+console.log(`🚀 Starting migration from .meta.json to _index.yaml\n`);
+migrateMetaToIndex(outputDir);
+console.log(`\n🎉 Migration finished!`);

package/package.json

@@ -0,0 +1,53 @@
+{
+  "name": "confluence-exporter",
+  "version": "1.0.0",
+  "type": "module",
+  "description": "Minimal standalone CLI tool to export Confluence spaces to Markdown",
+  "license": "MIT",
+  "main": "./dist/index.js",
+  "bin": {
+    "confluence-export": "./dist/index.js"
+  },
+  "scripts": {
+    "build": "npm run build:tsc",
+    "build:tsc": "tsc -p tsconfig.json",
+    "start": "node dist/index.js",
+    "clean": "rm -rf dist",
+    "rebuild": "npm run clean && npm run build",
+    "dev": "vite-node src/index.ts",
+    "dev:watch": "vite-node --watch src/index.ts",
+    "lint": "eslint . --ext .ts",
+    "test": "NODE_OPTIONS=--experimental-vm-modules jest",
+    "test:watch": "NODE_OPTIONS=--experimental-vm-modules jest --watch",
+    "test:coverage": "NODE_OPTIONS=--experimental-vm-modules jest --coverage",
+    "typecheck": "tsc --noEmit",
+    "prepublishOnly": "npm run build"
+  },
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "keywords": [
+    "confluence",
+    "markdown",
+    "exporter",
+    "cli"
+  ],
+  "dependencies": {
+    "dotenv": "^17.2.3",
+    "jsdom": "^27.0.1",
+    "minimist": "^1.2.8",
+    "prettier": "^3.6.2",
+    "webforai": "^2.1.1",
+    "yaml": "^2.8.1"
+  },
+  "devDependencies": {
+    "@types/jest": "^30.0.0",
+    "@types/minimist": "^1.2.5",
+    "@types/node": "^20.0.0",
+    "jest": "^30.2.0",
+    "ts-jest": "^29.4.5",
+    "typescript": "^5.0.0",
+    "vite": "^7.1.10",
+    "vite-node": "^3.2.4"
+  }
+}