File size: 29,848 Bytes
ffdff5d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 |
#!/usr/bin/env node
import { readFileSync, writeFileSync, existsSync, mkdirSync, readdirSync, statSync } from 'fs';
import { join, dirname, basename, extname } from 'path';
import { fileURLToPath } from 'url';
import matter from 'gray-matter';
import fetch from 'node-fetch';
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
// Configuration
const DEFAULT_INPUT = join(__dirname, 'output');
const DEFAULT_OUTPUT = join(__dirname, 'output');
const STATIC_FRONTMATTER_PATH = join(__dirname, 'static', 'frontmatter.mdx');
function parseArgs() {
const args = process.argv.slice(2);
const config = {
input: DEFAULT_INPUT,
output: DEFAULT_OUTPUT,
};
for (const arg of args) {
if (arg.startsWith('--input=')) {
config.input = arg.substring('--input='.length);
} else if (arg.startsWith('--output=')) {
config.output = arg.substring('--output='.length);
} else if (arg === '--help' || arg === '-h') {
console.log(`
π Notion Markdown to MDX Converter
Usage:
node mdx-converter.mjs [options]
Options:
--input=PATH Input directory or file (default: ${DEFAULT_INPUT})
--output=PATH Output directory (default: ${DEFAULT_OUTPUT})
--help, -h Show this help
Examples:
# Convert all markdown files in output directory
node mdx-converter.mjs
# Convert specific file
node mdx-converter.mjs --input=article.md --output=converted/
# Convert directory
node mdx-converter.mjs --input=markdown-files/ --output=mdx-files/
`);
process.exit(0);
} else if (!config.input) {
config.input = arg;
} else if (!config.output) {
config.output = arg;
}
}
return config;
}
/**
* Track which Astro components are used during transformations
*/
const usedComponents = new Set();
/**
* Track individual image imports needed
*/
const imageImports = new Map(); // src -> varName
/**
* Track external images that need to be downloaded
*/
const externalImagesToDownload = new Map(); // url -> localPath
/**
* Generate a variable name from image path
* @param {string} src - Image source path
* @returns {string} - Valid variable name
*/
function generateImageVarName(src) {
// Extract filename without extension and make it a valid JS variable
const filename = src.split('/').pop().replace(/\.[^.]+$/, '');
return filename.replace(/[^a-zA-Z0-9]/g, '_').replace(/^[0-9]/, 'img_$&');
}
/**
* Check if a URL is an external URL (HTTP/HTTPS)
* @param {string} url - URL to check
* @returns {boolean} - True if it's an external URL
*/
function isExternalImageUrl(url) {
try {
const urlObj = new URL(url);
// Just check if it's HTTP/HTTPS - we'll try to download everything
return urlObj.protocol === 'http:' || urlObj.protocol === 'https:';
} catch {
return false;
}
}
/**
* Extract image URL from Twitter/X page
* @param {string} tweetUrl - URL of the tweet
* @returns {Promise<string|null>} - URL of the image or null if not found
*/
async function extractTwitterImageUrl(tweetUrl) {
try {
const response = await fetch(tweetUrl, {
headers: {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
});
if (!response.ok) {
return null;
}
const html = await response.text();
// Try to find image URLs in meta tags (Twitter Card)
const metaImageMatch = html.match(/<meta property="og:image" content="([^"]+)"/);
if (metaImageMatch) {
let imageUrl = metaImageMatch[1];
// Try to get the large version
if (imageUrl.includes('?')) {
imageUrl = imageUrl.split('?')[0] + '?format=jpg&name=large';
}
return imageUrl;
}
// Fallback: try to find pbs.twimg.com URLs in the HTML
const pbsMatch = html.match(/https:\/\/pbs\.twimg\.com\/media\/([^"?]+)/);
if (pbsMatch) {
return `https://pbs.twimg.com/media/${pbsMatch[1]}?format=jpg&name=large`;
}
return null;
} catch (error) {
console.log(` β οΈ Failed to extract Twitter image: ${error.message}`);
return null;
}
}
/**
* Download an external URL and save it locally
* @param {string} imageUrl - External URL
* @param {string} outputDir - Directory to save the file
* @returns {Promise<string>} - Local path to the downloaded file
*/
async function downloadExternalImage(imageUrl, outputDir) {
try {
console.log(` π Downloading external URL: ${imageUrl}`);
// Create output directory if it doesn't exist
if (!existsSync(outputDir)) {
mkdirSync(outputDir, { recursive: true });
}
let actualImageUrl = imageUrl;
// Check if it's a Twitter/X URL
if (imageUrl.includes('twitter.com/') || imageUrl.includes('x.com/')) {
console.log(` π¦ Detected Twitter/X URL, attempting to extract image...`);
const extractedUrl = await extractTwitterImageUrl(imageUrl);
if (extractedUrl) {
actualImageUrl = extractedUrl;
console.log(` β
Extracted image URL: ${extractedUrl}`);
} else {
console.log(` β οΈ Could not automatically extract image from Twitter/X`);
console.log(` π‘ Manual download required:`);
console.log(` 1. Open ${imageUrl} in your browser`);
console.log(` 2. Right-click on the image and "Save image as..."`);
console.log(` 3. Save it to: app/src/content/assets/image/`);
throw new Error('Twitter/X images require manual download');
}
}
// Generate filename from URL
const urlObj = new URL(actualImageUrl);
const pathname = urlObj.pathname;
// Determine file extension - try to get it from URL, default to jpg
let extension = 'jpg';
if (pathname.includes('.')) {
const urlExtension = pathname.split('.').pop().toLowerCase();
if (['jpg', 'jpeg', 'png', 'gif', 'svg', 'webp', 'bmp', 'tiff'].includes(urlExtension)) {
extension = urlExtension;
}
}
// Generate unique filename
const filename = `external_${Date.now()}_${Math.random().toString(36).substr(2, 9)}.${extension}`;
const localPath = join(outputDir, filename);
// Try to download the URL
const response = await fetch(actualImageUrl, {
headers: {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
});
if (!response.ok) {
throw new Error(`HTTP ${response.status}: ${response.statusText}`);
}
const buffer = await response.buffer();
// Validate that we actually got data
if (buffer.length === 0) {
throw new Error('Empty response');
}
// Validate that it's actually an image, not HTML
const contentType = response.headers.get('content-type');
if (contentType && contentType.includes('text/html')) {
throw new Error('Downloaded content is HTML, not an image');
}
// Save to local file
writeFileSync(localPath, buffer);
console.log(` β
Downloaded: ${filename} (${buffer.length} bytes)`);
return localPath;
} catch (error) {
console.log(` β Failed to download ${imageUrl}: ${error.message}`);
throw error;
}
}
/**
* Process external images in content and download them
* @param {string} content - Markdown content
* @param {string} outputDir - Directory to save downloaded images
* @returns {Promise<string>} - Content with external images replaced by local paths
*/
async function processExternalImages(content, outputDir) {
console.log(' π Processing external images...');
let processedCount = 0;
let downloadedCount = 0;
// Find all external image URLs in markdown format: 
const externalImageRegex = /!\[([^\]]*)\]\(([^)]+)\)/g;
let match;
const externalImages = new Map(); // url -> alt text
// First pass: collect all external image URLs
while ((match = externalImageRegex.exec(content)) !== null) {
const alt = match[1];
const url = match[2];
if (isExternalImageUrl(url)) {
externalImages.set(url, alt);
console.log(` π Found external image: ${url}`);
}
}
if (externalImages.size === 0) {
console.log(' βΉοΈ No external images found');
return content;
}
// Second pass: download images and replace URLs
let processedContent = content;
for (const [url, alt] of externalImages) {
try {
// Download the image
const localPath = await downloadExternalImage(url, outputDir);
const relativePath = `./assets/image/${basename(localPath)}`;
// Replace the URL in content
processedContent = processedContent.replace(
new RegExp(`!\\[${alt.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')}\\]\\(${url.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')}\\)`, 'g'),
``
);
downloadedCount++;
processedCount++;
} catch (error) {
console.log(` β οΈ Skipping external image due to download failure: ${url}`);
}
}
if (downloadedCount > 0) {
console.log(` β
Downloaded ${downloadedCount} external image(s)`);
}
return processedContent;
}
/**
* Detect and track Astro components used in the content
* @param {string} content - MDX content
*/
function detectAstroComponents(content) {
console.log(' π Detecting Astro components in content...');
let detectedCount = 0;
// Known Astro components that should be auto-imported
const knownComponents = [
'HtmlEmbed', 'Image', 'Note', 'Sidenote', 'Wide', 'FullWidth',
'Accordion', 'Quote', 'Reference', 'Glossary', 'Stack', 'ThemeToggle',
'RawHtml', 'HfUser'
];
// Find all JSX elements that look like Astro components
// Pattern: <ComponentName ... />
const componentMatches = content.match(/<([A-Z][a-zA-Z0-9]*)\s*[^>]*\/?>/g);
if (componentMatches) {
for (const match of componentMatches) {
// Extract component name from the JSX element
const componentMatch = match.match(/<([A-Z][a-zA-Z0-9]*)/);
if (componentMatch) {
const componentName = componentMatch[1];
// Only track known Astro components (skip HTML elements)
if (knownComponents.includes(componentName) && !usedComponents.has(componentName)) {
usedComponents.add(componentName);
detectedCount++;
console.log(` π¦ Found component: ${componentName}`);
}
}
}
}
if (detectedCount > 0) {
console.log(` β
Detected ${detectedCount} new Astro component(s)`);
} else {
console.log(` βΉοΈ No new Astro components detected`);
}
}
/**
* Add required component imports to the frontmatter
* @param {string} content - MDX content
* @returns {string} - Content with component imports
*/
function addComponentImports(content) {
console.log(' π¦ Adding component and image imports...');
let imports = [];
// Add component imports
if (usedComponents.size > 0) {
const componentImports = Array.from(usedComponents)
.map(component => `import ${component} from '../components/${component}.astro';`);
imports.push(...componentImports);
console.log(` β
Importing components: ${Array.from(usedComponents).join(', ')}`);
}
// Add image imports
if (imageImports.size > 0) {
const imageImportStatements = Array.from(imageImports.entries())
.map(([src, varName]) => `import ${varName} from '${src}';`);
imports.push(...imageImportStatements);
console.log(` β
Importing ${imageImports.size} image(s)`);
}
if (imports.length === 0) {
console.log(' βΉοΈ No imports needed');
return content;
}
const importBlock = imports.join('\n');
// Insert imports after frontmatter
const frontmatterEnd = content.indexOf('---', 3) + 3;
if (frontmatterEnd > 2) {
return content.slice(0, frontmatterEnd) + '\n\n' + importBlock + '\n\n' + content.slice(frontmatterEnd);
} else {
// No frontmatter, add at beginning
return importBlock + '\n\n' + content;
}
}
/**
* Load static frontmatter from file
* @returns {object} - Static frontmatter data
*/
function loadStaticFrontmatter() {
try {
if (existsSync(STATIC_FRONTMATTER_PATH)) {
const staticContent = readFileSync(STATIC_FRONTMATTER_PATH, 'utf8');
const { data } = matter(staticContent);
console.log(' β
Loaded static frontmatter from file');
return data;
}
console.log(' βΉοΈ No static frontmatter file found');
return {};
} catch (error) {
console.log(` β οΈ Failed to load static frontmatter: ${error.message}`);
return {};
}
}
/**
* Ensure proper frontmatter for MDX using static file first, then existing data
* @param {string} content - MDX content
* @param {string} pageId - Notion page ID (optional, kept for compatibility but ignored)
* @param {string} notionToken - Notion API token (optional, kept for compatibility but ignored)
* @returns {string} - Content with proper frontmatter
*/
async function ensureFrontmatter(content, pageId = null, notionToken = null) {
console.log(' π Ensuring proper frontmatter...');
// Load static frontmatter first (highest priority)
const staticData = loadStaticFrontmatter();
if (!content.startsWith('---')) {
// No frontmatter in content, use static + basic defaults
let baseData = { ...staticData };
// Add basic defaults for required fields if not in static
if (!baseData.title) baseData.title = 'Article';
if (!baseData.published) {
baseData.published = new Date().toLocaleDateString('en-US', {
year: 'numeric',
month: 'short',
day: '2-digit'
});
}
if (baseData.tableOfContentsAutoCollapse === undefined) {
baseData.tableOfContentsAutoCollapse = true;
}
const frontmatter = matter.stringify('', baseData);
console.log(' β
Applied static frontmatter to content without frontmatter');
return frontmatter + content;
}
// Parse existing frontmatter and merge with static (static takes priority)
try {
const { data: existingData, content: body } = matter(content);
// Merge: existing data first, then static data overrides
const mergedData = { ...existingData, ...staticData };
// Ensure required fields if still missing after merge
if (!mergedData.title) mergedData.title = 'Article';
if (!mergedData.published) {
mergedData.published = new Date().toLocaleDateString('en-US', {
year: 'numeric',
month: 'short',
day: '2-digit'
});
}
if (mergedData.tableOfContentsAutoCollapse === undefined) {
mergedData.tableOfContentsAutoCollapse = true;
}
const enhancedContent = matter.stringify(body, mergedData);
console.log(' β
Merged static and existing frontmatter');
return enhancedContent;
} catch (error) {
console.log(' β οΈ Could not parse frontmatter, keeping as is');
return content;
}
}
/**
* Generate basic frontmatter
* @returns {string} - Basic frontmatter
*/
function generateBasicFrontmatter() {
const currentDate = new Date().toLocaleDateString('en-US', {
year: 'numeric',
month: 'short',
day: '2-digit'
});
return `---
title: "Notion Article"
published: "${currentDate}"
tableOfContentsAutoCollapse: true
---
`;
}
/**
* Check if a line is a table line
* @param {string} line - Line to check
* @returns {boolean} - True if it's a table line
*/
function isTableLine(line) {
const trimmed = line.trim();
return trimmed.startsWith('|') && trimmed.endsWith('|');
}
/**
* Check if a line is a list item
* @param {string} line - Line to check
* @returns {boolean} - True if it's a list item
*/
function isListItem(line) {
const trimmed = line.trim();
// Match: * -, + (bullet points) or 1. 2. 3. (numbered lists)
return /^\s*[\*\-\+]\s/.test(trimmed) || /^\s*\d+\.\s/.test(trimmed);
}
/**
* Add a blank line after each markdown table and list
* @param {string} content - MDX content
* @returns {string} - Content with blank lines after tables and lists
*/
function addBlankLineAfterTablesAndLists(content) {
console.log(' π Adding blank lines after tables and lists...');
let addedTableCount = 0;
let addedListCount = 0;
const lines = content.split('\n');
const result = [];
for (let i = 0; i < lines.length; i++) {
result.push(lines[i]);
// Check if current line is the end of a table
if (isTableLine(lines[i])) {
// Look ahead to see if this is the last line of a table
let isLastTableLine = false;
// Check if next line is empty or doesn't start with |
if (i + 1 >= lines.length ||
lines[i + 1].trim() === '' ||
!isTableLine(lines[i + 1])) {
// Look back to find if we're actually inside a table
let tableLineCount = 0;
for (let j = i; j >= 0 && isTableLine(lines[j]); j--) {
tableLineCount++;
}
// Only add blank line if we found at least 2 table lines (making it a real table)
if (tableLineCount >= 2) {
isLastTableLine = true;
}
}
if (isLastTableLine) {
addedTableCount++;
result.push(''); // Add blank line
}
}
// Check if current line is the end of a list
else if (isListItem(lines[i])) {
// Look ahead to see if this is the last line of a list
let isLastListItem = false;
// Check if next line is empty or doesn't start with list marker
if (i + 1 >= lines.length ||
lines[i + 1].trim() === '' ||
!isListItem(lines[i + 1])) {
isLastListItem = true;
}
if (isLastListItem) {
addedListCount++;
result.push(''); // Add blank line
}
}
}
if (addedTableCount > 0 || addedListCount > 0) {
console.log(` β
Added blank line after ${addedTableCount} table(s) and ${addedListCount} list(s)`);
} else {
console.log(' βΉοΈ No tables or lists found to process');
}
return result.join('\n');
}
/**
* Transform markdown images to Image components
* @param {string} content - Markdown content
* @returns {string} - Content with Image components
*/
function transformMarkdownImages(content) {
console.log(' πΌοΈ Transforming markdown images to Image components...');
let transformedCount = 0;
// Transform markdown images:  -> <Image src={varName} alt="alt" />
content = content.replace(/!\[([^\]]*)\]\(([^)]+)\)/g, (match, alt, src) => {
transformedCount++;
// Clean up the src path - remove /media/ prefix and use relative path
let cleanSrc = src;
if (src.startsWith('/media/')) {
cleanSrc = src.replace('/media/', './assets/image/');
}
// Generate variable name for the image import
const varName = generateImageVarName(cleanSrc);
// Add to imageImports if not already present
if (!imageImports.has(cleanSrc)) {
imageImports.set(cleanSrc, varName);
}
// Extract filename for alt text if none provided
const finalAlt = alt || src.split('/').pop().split('.')[0];
return `<Image src={${varName}} alt="${finalAlt}" />`;
});
if (transformedCount > 0) {
console.log(` β
Transformed ${transformedCount} markdown image(s) to Image components with imports`);
} else {
console.log(' βΉοΈ No markdown images found to transform');
}
return content;
}
/**
* Add proper spacing around Astro components
* @param {string} content - MDX content
* @returns {string} - Content with proper spacing around components
*/
function addSpacingAroundComponents(content) {
console.log(' π Adding spacing around Astro components...');
let processedContent = content;
let spacingCount = 0;
// Known Astro components that should have spacing
const knownComponents = [
'HtmlEmbed', 'Image', 'Note', 'Sidenote', 'Wide', 'FullWidth',
'Accordion', 'Quote', 'Reference', 'Glossary', 'Stack', 'ThemeToggle',
'RawHtml', 'HfUser', 'Figure'
];
// Process each component type
for (const component of knownComponents) {
// Pattern for components with content: <Component>...</Component>
// Process this first to handle the complete component structure
const withContentPattern = new RegExp(`(<${component}[^>]*>)([\\s\\S]*?)(<\\/${component}>)`, 'g');
processedContent = processedContent.replace(withContentPattern, (match, openTag, content, closeTag) => {
spacingCount++;
// Ensure blank line before opening tag and after closing tag
// Also ensure closing tag is on its own line
const trimmedContent = content.trim();
return `\n\n${openTag}\n${trimmedContent}\n${closeTag}\n\n`;
});
// Pattern for self-closing components: <Component ... />
const selfClosingPattern = new RegExp(`(<${component}[^>]*\\/?>)`, 'g');
processedContent = processedContent.replace(selfClosingPattern, (match) => {
spacingCount++;
return `\n\n${match}\n\n`;
});
}
// Clean up excessive newlines (more than 2 consecutive)
processedContent = processedContent.replace(/\n{3,}/g, '\n\n');
if (spacingCount > 0) {
console.log(` β
Added spacing around ${spacingCount} component(s)`);
} else {
console.log(' βΉοΈ No components found to add spacing around');
}
return processedContent;
}
/**
* Fix smart quotes (curly quotes) and replace them with straight quotes
* @param {string} content - Markdown content
* @returns {string} - Content with fixed quotes
*/
function fixSmartQuotes(content) {
console.log(' βοΈ Fixing smart quotes (curly quotes)...');
let fixedCount = 0;
const originalContent = content;
// Replace opening smart double quotes (\u201C) with straight quotes (")
content = content.replace(/\u201C/g, '"');
// Replace closing smart double quotes (\u201D) with straight quotes (")
content = content.replace(/\u201D/g, '"');
// Replace opening smart single quotes (\u2018) with straight quotes (')
content = content.replace(/\u2018/g, "'");
// Replace closing smart single quotes (\u2019) with straight quotes (')
content = content.replace(/\u2019/g, "'");
// Count the number of replacements made
fixedCount = 0;
for (let i = 0; i < originalContent.length; i++) {
const char = originalContent[i];
if (char === '\u201C' || char === '\u201D' || char === '\u2018' || char === '\u2019') {
fixedCount++;
}
}
if (fixedCount > 0) {
console.log(` β
Fixed ${fixedCount} smart quote(s)`);
} else {
console.log(' βΉοΈ No smart quotes found');
}
return content;
}
/**
* Main MDX processing function that applies all transformations
* @param {string} content - Raw Markdown content
* @param {string} pageId - Notion page ID (optional)
* @param {string} notionToken - Notion API token (optional)
* @param {string} outputDir - Output directory for downloaded images (optional)
* @returns {string} - Processed MDX content compatible with Astro
*/
async function processMdxContent(content, pageId = null, notionToken = null, outputDir = null) {
console.log('π§ Processing for Astro MDX compatibility...');
// Clear previous tracking
usedComponents.clear();
imageImports.clear();
externalImagesToDownload.clear();
let processedContent = content;
// Fix smart quotes first
processedContent = fixSmartQuotes(processedContent);
// Process external images first (before other transformations)
if (outputDir) {
// Create a temporary external images directory in the output folder
const externalImagesDir = join(outputDir, 'external-images');
processedContent = await processExternalImages(processedContent, externalImagesDir);
}
// Apply essential steps only
processedContent = await ensureFrontmatter(processedContent, pageId, notionToken);
// Add blank lines after tables and lists
processedContent = addBlankLineAfterTablesAndLists(processedContent);
// Transform markdown images to Image components
processedContent = transformMarkdownImages(processedContent);
// Add spacing around Astro components
processedContent = addSpacingAroundComponents(processedContent);
// Detect Astro components used in the content before adding imports
detectAstroComponents(processedContent);
// Add component imports at the end
processedContent = addComponentImports(processedContent);
return processedContent;
}
/**
* Convert a single markdown file to MDX
* @param {string} inputFile - Input markdown file
* @param {string} outputDir - Output directory
* @param {string} pageId - Notion page ID (optional)
* @param {string} notionToken - Notion API token (optional)
*/
async function convertFileToMdx(inputFile, outputDir, pageId = null, notionToken = null) {
const filename = basename(inputFile, '.md');
const outputFile = join(outputDir, `${filename}.mdx`);
console.log(`π Converting: ${basename(inputFile)} β ${basename(outputFile)}`);
try {
const markdownContent = readFileSync(inputFile, 'utf8');
const mdxContent = await processMdxContent(markdownContent, pageId, notionToken, outputDir);
writeFileSync(outputFile, mdxContent);
console.log(` β
Converted: ${outputFile}`);
// Show file size
const inputSize = Math.round(markdownContent.length / 1024);
const outputSize = Math.round(mdxContent.length / 1024);
console.log(` π Input: ${inputSize}KB β Output: ${outputSize}KB`);
} catch (error) {
console.error(` β Failed to convert ${inputFile}: ${error.message}`);
}
}
/**
* Convert all markdown files in a directory to MDX
* @param {string} inputPath - Input path (file or directory)
* @param {string} outputDir - Output directory
* @param {string} pageId - Notion page ID (optional)
* @param {string} notionToken - Notion API token (optional)
*/
async function convertToMdx(inputPath, outputDir, pageId = null, notionToken = null) {
console.log('π Notion Markdown to Astro MDX Converter');
console.log(`π Input: ${inputPath}`);
console.log(`π Output: ${outputDir}`);
// Check if input exists
if (!existsSync(inputPath)) {
console.error(`β Input not found: ${inputPath}`);
process.exit(1);
}
try {
// Ensure output directory exists
if (!existsSync(outputDir)) {
mkdirSync(outputDir, { recursive: true });
}
let filesToConvert = [];
if (statSync(inputPath).isDirectory()) {
// Convert all .md files in directory
const files = readdirSync(inputPath);
filesToConvert = files
.filter(file => file.endsWith('.md') && !file.includes('.raw.md'))
.map(file => join(inputPath, file));
} else if (inputPath.endsWith('.md')) {
// Convert single file
filesToConvert = [inputPath];
} else {
console.error('β Input must be a .md file or directory containing .md files');
process.exit(1);
}
if (filesToConvert.length === 0) {
console.log('βΉοΈ No .md files found to convert');
return;
}
console.log(`π Found ${filesToConvert.length} file(s) to convert`);
// Convert each file
for (const file of filesToConvert) {
await convertFileToMdx(file, outputDir, pageId, notionToken);
}
console.log(`β
Conversion completed! ${filesToConvert.length} file(s) processed`);
} catch (error) {
console.error('β Conversion failed:', error.message);
process.exit(1);
}
}
export { convertToMdx };
function main() {
const config = parseArgs();
convertToMdx(config.input, config.output);
console.log('π MDX conversion completed!');
}
if (import.meta.url === `file://${process.argv[1]}`) {
main();
}
|