Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 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 | 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 13x 13x 13x 13x 13x 7x 7x 7x 7x 7x 1x 1x 1x 1x 1x 1x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 1x 1x 1x 1x 1x 1x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 12x 12x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 14x 14x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 1x 1x 1x 1x 6x 6x 6x 6x 1x 1x 1x 1x 1x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 1x 1x 1x 1x 1x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 6x 13x 13x 13x 13x 13x 13x 6x 6x 6x 1x 1x 1x 1x 1x 1x 1x 8x 8x 8x 8x 8x 8x 8x 8x 8x 8x 8x 8x 8x 1x 1x 1x 1x 1x 1x 7x 7x 7x 7x 1x 1x 1x 1x 1x 1x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 9x 9x 9x 9x 9x 8x 9x 1x 1x 1x 1x 1x 1x 1x 7x 7x 7x 7x 7x 9x 9x 7x 7x 7x 7x 9x 7x 9x 9x 1x 1x 1x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 1x 1x 1x 1x 1x 26x 26x 26x 26x 26x 26x 26x 1x 1x 1x 1x 1x 1x 1x 1x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 12x 12x 12x 12x 12x 12x 12x 12x 12x 12x 12x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 10x 10x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 5x 1x 1x 5x 2x 2x 5x 1x 1x 1x 1x 1x 1x 1x 9x 9x 9x 9x 9x 2x 2x 2x 2x 2x 7x 7x 7x 7x 7x 7x 9x 1x 1x 9x 2x 2x 2x 2x 9x 1x 1x 1x 1x 1x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 10x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x | /**
* LLM-friendly Markdown formatter for git-ingest output
* Generates structured, semantic markdown optimized for AI consumption
*/
import fs from "fs/promises";
import path from "path";
import pLimit from "p-limit";
import { detectLanguage, getLanguageStats } from "./language-detector.js";
import { Config } from "./config.js";
import { PERFORMANCE_CONSTANTS } from "./constants.js";
/**
* Generate table of contents for the document
* @param {Array} categories - File categories
* @returns {string} - Markdown table of contents
*/
function generateTableOfContents(categories) {
const toc = [
"## 📑 Table of Contents",
"",
"- [📊 Project Overview](#-project-overview)",
"- [📈 Statistics](#-statistics)",
"- [🏗️ Directory Structure](#️-directory-structure)",
"- [📁 Files by Category](#-files-by-category)"
];
// Add category sections to TOC
categories.forEach((category) => {
const anchor = category.name.toLowerCase().replace(/[^a-z0-9]/gu, "-");
const hexCode = 16;
toc.push(
` - [${category.emoji} ${category.name}](#${category.emoji.codePointAt(0).toString(hexCode)}-${anchor})`
);
});
toc.push("- [📋 Complete File Listing](#-complete-file-listing)");
toc.push("");
return toc.join("\n");
}
/**
* Generate project overview section
* @param {string} dirPath - Project directory path
* @param {Object} stats - Project statistics
* @returns {string} - Markdown overview section
*/
function generateProjectOverview(dirPath, stats) {
const projectName = path.basename(path.resolve(dirPath));
const now = new Date();
return [
"## 📊 Project Overview",
"",
`**Project:** \`${projectName}\` `,
`**Path:** \`${path.resolve(dirPath)}\` `,
`**Generated:** ${now.toISOString()} `,
`**Total Files:** ${stats.totalFiles} `,
`**Total Size:** ${formatFileSize(stats.totalSizeBytes)} `,
"",
"### 🎯 Quick Summary",
"",
`This document contains a comprehensive analysis of the **${projectName}** project, `,
"including its complete directory structure and the full content of all text files. ",
"The content is organized in a hierarchical, LLM-friendly format with proper syntax ",
"highlighting and metadata for optimal AI processing.",
""
].join("\n");
}
/**
* Generate statistics section
* @param {Object} stats - Project statistics
* @param {Object} languageStats - Language statistics
* @returns {string} - Markdown statistics section
*/
function generateStatistics(stats, languageStats) {
const sections = [
"## 📈 Statistics",
"",
"### 📊 File Type Distribution",
"",
"| Category | Files | Percentage |",
"| --- | --- | --- |"
];
// Add category statistics
Object.entries(languageStats.byCategory)
.sort(([, a], [, b]) => b.count - a.count)
.forEach(([category, data]) => {
const percentage = ((data.count / stats.totalFiles) * 100).toFixed(1);
sections.push(`| ${category} | ${data.count} | ${percentage}% |`);
});
sections.push("");
sections.push("### 💻 Programming Languages");
sections.push("");
sections.push("| Language | Files | Primary Category |");
sections.push("| --- | --- | --- |");
// Add language statistics
const maxLanguagesToShow = 15;
Object.entries(languageStats.byLanguage)
.sort(([, a], [, b]) => b.count - a.count)
.slice(0, maxLanguagesToShow) // Top languages
.forEach(([language, data]) => {
const detection = detectLanguage(data.files[0]);
sections.push(`| ${language} | ${data.count} | ${detection.category} |`);
});
sections.push("");
sections.push("### 📏 Size Analysis");
sections.push("");
sections.push(
`- **Total Project Size:** ${formatFileSize(stats.totalSizeBytes)}`
);
sections.push(
`- **Average File Size:** ${formatFileSize(stats.totalSizeBytes / stats.totalFiles)}`
);
sections.push(
`- **Text Files:** ${stats.textFiles} (${((stats.textFiles / stats.totalFiles) * 100).toFixed(1)}%)`
);
if (stats.binaryFiles > 0) {
sections.push(
`- **Binary Files:** ${stats.binaryFiles} (excluded from content)`
);
}
if (stats.largeFiles > 0) {
sections.push(`- **Large Files:** ${stats.largeFiles} (may be truncated)`);
}
sections.push("");
return sections.join("\n");
}
/**
* Generate directory structure section
* @param {Array} treeOutput - Directory tree lines
* @returns {string} - Markdown directory structure section
*/
function generateDirectoryStructure(treeOutput) {
return [
"## 🏗️ Directory Structure",
"",
"```",
...treeOutput,
"```",
""
].join("\n");
}
/**
* Generate files by category section
* @param {Object} languageStats - Language statistics
* @returns {string} - Markdown files by category section
*/
function generateFilesByCategory(languageStats) {
const sections = ["## 📁 Files by Category", ""];
const categoryEmojis = {
"Web Frontend": "🌐",
"Backend/Server": "⚙️",
"Systems/Low-level": "🔧",
"Functional": "🧮",
"Scripting": "📜",
"Data/Config": "⚙️",
"Documentation": "📖",
"Mobile": "📱",
"DevOps": "🚀",
"Other": "📄"
};
Object.entries(languageStats.byCategory)
.sort(([, a], [, b]) => b.count - a.count)
.forEach(([category, data]) => {
const emoji = categoryEmojis[category] || "📄";
sections.push(`### ${emoji} ${category}`);
sections.push("");
sections.push(`**Languages:** ${data.languages.join(", ")} `);
sections.push(`**File Count:** ${data.count}`);
sections.push("");
});
return sections.join("\n");
}
/**
* Generate file header with metadata
* @param {string} filePath - File path
* @param {Object} stats - File stats
* @param {Object} detection - Language detection result
* @returns {string} - Markdown file header
*/
function generateFileHeader(filePath, stats, detection) {
const relativePath = path.relative(process.cwd(), filePath);
const fileName = path.basename(filePath);
return [
`### 📄 \`${fileName}\``,
"",
`**Path:** \`${relativePath}\` `,
`**Size:** ${formatFileSize(stats.size)} `,
`**Language:** ${detection.language} (${detection.confidence} confidence) `,
`**Category:** ${detection.category} `,
""
].join("\n");
}
/**
* Generate file content block
* @param {string} content - File content
* @param {Object} detection - Language detection result
* @returns {string} - Markdown code block
*/
function generateFileContent(content, detection) {
const language = detection.language === "text" ? "" : detection.language;
return [`\`\`\`${language}`, content.trim(), "```", ""].join("\n");
}
/**
* Generate complete file listing section with parallel processing
* @param {Array} filePaths - Array of file paths
* @param {Object} options - Processing options
* @returns {string} - Markdown complete file listing
*/
async function generateCompleteFileListing(filePaths, options = {}) {
const config = options.config || new Config();
const sections = [
"## 📋 Complete File Listing",
"",
"The following section contains the complete content of all text files in the project, ",
"organized with proper syntax highlighting and metadata for optimal LLM processing.",
""
];
let processedCount = 0;
let skippedCount = 0;
const { progress } = options;
// Create concurrency limiter based on performance constants
const DYNAMIC_SCALING_DIVISOR = 5;
const concurrencyLimit = Math.min(
PERFORMANCE_CONSTANTS.DEFAULT_CONCURRENCY_LIMIT,
Math.max(1, Math.floor(filePaths.length / DYNAMIC_SCALING_DIVISOR)) // Dynamic scaling for file reading
);
const limit = pLimit(concurrencyLimit);
// Process files with controlled concurrency
const processFile = async (filePath) => {
try {
// Check if file should be skipped
const { shouldSkipForContent } = await import("./tree-generator.js");
const skipInfo = shouldSkipForContent(filePath, { ...options, config });
const stats = await fs.stat(filePath);
const detection = detectLanguage(filePath);
if (skipInfo.skip) {
// Generate placeholder for skipped files
const fileHeader = generateFileHeader(filePath, stats, detection);
const skipNotice = `> **⏭️ Skipped:** ${skipInfo.reason}`;
skippedCount++;
if (progress) {
progress.reportFileProgress(filePath, 0, "skipped");
}
return { content: `${fileHeader}${skipNotice}\n\n`, type: "skipped" };
}
// Generate file header
const fileHeader = generateFileHeader(filePath, stats, detection);
// Read and add content
try {
let content;
if (stats.size > config.maxFileSizeBytes) {
// Use truncation for very large files
const maxSize = config.options.TRUNCATE_SIZE_BYTES;
const handle = await fs.open(filePath, "r");
const buffer = Buffer.alloc(maxSize);
const { bytesRead } = await handle.read(buffer, 0, maxSize, 0);
await handle.close();
content = buffer.subarray(0, bytesRead).toString("utf8");
if (stats.size > maxSize) {
content += `\n\n[File truncated - showing first ${formatFileSize(maxSize)} of ${formatFileSize(stats.size)} total]`;
}
} else {
content = await fs.readFile(filePath, "utf8");
}
const fileContent = generateFileContent(content, detection);
processedCount++;
if (progress) {
progress.reportFileProgress(filePath, stats.size, "processed");
}
return { content: `${fileHeader}${fileContent}`, type: "processed" };
} catch (readError) {
const errorContent = `> **❌ Error:** Could not read file content: ${readError.message}\n\n`;
if (progress) {
progress.reportFileProgress(filePath, 0, "error");
}
return { content: `${fileHeader}${errorContent}`, type: "error" };
}
} catch {
if (progress) {
progress.reportFileProgress(filePath, 0, "error");
}
return { content: "", type: "error" };
}
};
// Execute file processing with concurrency control
const results = await Promise.allSettled(
filePaths.map((filePath) => limit(() => processFile(filePath)))
);
// Collect successful results and maintain order
const fileContents = results
.filter((result) => result.status === "fulfilled" && result.value.content)
.map((result) => result.value.content);
sections.push(...fileContents);
// Add processing summary
sections.push("---");
sections.push("");
sections.push("### 📊 Processing Summary");
sections.push("");
sections.push(`- **Files Processed:** ${processedCount}`);
sections.push(`- **Files Skipped:** ${skippedCount}`);
sections.push(`- **Total Files:** ${filePaths.length}`);
sections.push(`- **Concurrency Limit:** ${concurrencyLimit}`);
sections.push("");
return sections.join("\n");
}
/**
* Format file size in human readable format
* @param {number} bytes - Size in bytes
* @returns {string} - Formatted size string
*/
function formatFileSize(bytes) {
if (bytes === 0) return "0 B";
const k = 1024;
const sizes = ["B", "KB", "MB", "GB"];
const i = Math.floor(Math.log(bytes) / Math.log(k));
return `${parseFloat((bytes / Math.pow(k, i)).toFixed(1))} ${sizes[i]}`;
}
/**
* Save markdown tree to file with enhanced LLM-friendly formatting
* @param {string} dirPath - Directory path
* @param {string} fileName - Output file name
* @param {Array} treeOutput - Directory tree output
* @param {Object} options - Options
*/
export async function saveMarkdownTreeToFile(
dirPath,
fileName,
treeOutput,
options = {}
) {
try {
// Generate project statistics
const { getAllFilePaths } = await import("./tree-generator.js");
const filePaths = await getAllFilePaths(dirPath, options);
const languageStats = getLanguageStats(filePaths);
// Calculate file statistics
let totalSize = 0;
let textFiles = 0;
let binaryFiles = 0;
let largeFiles = 0;
for (const filePath of filePaths) {
try {
const stats = await fs.stat(filePath);
totalSize += stats.size;
const { shouldSkipForContent } = await import("./tree-generator.js");
const skipInfo = shouldSkipForContent(filePath, options);
if (skipInfo.skip) {
if (skipInfo.reason.includes("Binary")) {
binaryFiles++;
} else if (skipInfo.reason.includes("too large")) {
largeFiles++;
}
} else {
textFiles++;
}
} catch {
// Skip files that can't be accessed
}
}
const stats = {
totalFiles: filePaths.length,
textFiles,
binaryFiles,
largeFiles,
totalSizeBytes: totalSize
};
// Create categories for TOC
const categories = Object.entries(languageStats.byCategory)
.sort(([, a], [, b]) => b.count - a.count)
.map(([name]) => ({
name,
emoji: getCategoryEmoji(name)
}));
// Generate markdown content
const projectName = path.basename(path.resolve(dirPath));
const sections = [
"# 🚀 Project Analysis Report",
"",
`Directory structure for: ${projectName}`,
"",
"## 🎯 LLM-Optimized Codebase Analysis",
"",
"This document provides a comprehensive, structured analysis of the codebase optimized for ",
"Large Language Model (LLM) processing. The content is organized with semantic markup, ",
"proper syntax highlighting, and hierarchical structure for enhanced AI comprehension.",
"",
generateTableOfContents(categories),
generateProjectOverview(dirPath, stats),
generateStatistics(stats, languageStats),
generateDirectoryStructure(treeOutput),
generateFilesByCategory(languageStats)
];
const content = sections.join("\n");
await fs.writeFile(fileName, content, "utf8");
if (options.verbose) {
console.log(`📝 Markdown tree saved to ${fileName}`);
}
} catch (error) {
throw new Error(`Failed to save markdown tree to file: ${error.message}`);
}
}
/**
* Append file contents to markdown file with enhanced formatting
* @param {Array} filePaths - Array of file paths
* @param {string} outputFilePath - Output file path
* @param {Object} options - Processing options
*/
export async function appendMarkdownFileContents(
filePaths,
outputFilePath,
options = {}
) {
if (!Array.isArray(filePaths) || filePaths.length === 0) {
if (options.verbose) {
console.log("📝 No files to process for markdown output");
}
return;
}
try {
const completeFileListing = await generateCompleteFileListing(
filePaths,
options
);
await fs.appendFile(outputFilePath, completeFileListing, "utf8");
if (options.verbose) {
console.log(`📝 File contents appended to ${outputFilePath}`);
}
} catch (error) {
throw new Error(
`Failed to append markdown file contents: ${error.message}`
);
}
}
/**
* Get emoji for category
* @param {string} category - Category name
* @returns {string} - Emoji
*/
function getCategoryEmoji(category) {
const emojis = {
"Web Frontend": "🌐",
"Backend/Server": "⚙️",
"Systems/Low-level": "🔧",
"Functional": "🧮",
"Scripting": "📜",
"Data/Config": "⚙️",
"Documentation": "📖",
"Mobile": "📱",
"DevOps": "🚀",
"Other": "📄"
};
return emojis[category] || "📄";
}
export {
generateTableOfContents,
generateProjectOverview,
generateStatistics,
generateDirectoryStructure,
generateFilesByCategory,
generateCompleteFileListing
};
export default {
saveMarkdownTreeToFile,
appendMarkdownFileContents,
generateTableOfContents,
generateProjectOverview,
generateStatistics,
generateDirectoryStructure,
generateFilesByCategory,
generateCompleteFileListing
};
|