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 | 2x 2x 2x 2x 2x 2x 2x 2x 2x 57x 2x 57x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 66x 66x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 4x 1x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 3x 3x 2x 3x 3x 3x 2x 3x 2x 2x 3x 2x 1x 1x 2x 2x 2x 2x 2x 2x 2x 2x 2x 1x 1x 1x 1x 1x 1x 1x 1x 1x 2x 2x 2x 2x 2x 2x 2x 2x 4x 2x 2x 2x 2x 2x 2x 2x 2x 6x 3x 2x 2x 2x 3x 2x 1x 2x 2x 1x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 10x 10x 10x 10x 2x 8x 6x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x | // src/services/flyerFileHandler.server.ts
import path from 'path';
import sharp from 'sharp';
import type { Dirent } from 'node:fs';
import type { Job } from 'bullmq';
import type { Logger } from 'pino';
import { ImageConversionError, PdfConversionError, UnsupportedFileTypeError } from './processingErrors';
import type { FlyerJobData } from '../types/job-data';
// Define the image formats supported by the AI model
const SUPPORTED_IMAGE_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.webp', '.heic', '.heif'];
// Define image formats that are not directly supported but can be converted to PNG.
const CONVERTIBLE_IMAGE_EXTENSIONS = ['.gif', '.tiff', '.svg', '.bmp'];
export interface IFileSystem {
readdir(path: string, options: { withFileTypes: true }): Promise<Dirent[]>;
unlink(path: string): Promise<void>;
rename(oldPath: string, newPath: string): Promise<void>;
}
export interface ICommandExecutor {
(command: string): Promise<{ stdout: string; stderr: string }>;
}
/**
* This class encapsulates the logic for handling different file types (PDF, images)
* and preparing them for AI processing.
*/
export class FlyerFileHandler {
constructor(
private fs: IFileSystem,
private exec: ICommandExecutor,
) {}
/**
* Executes the pdftocairo command to convert the PDF.
*/
private async _executePdfConversion(
filePath: string,
outputFilePrefix: string,
logger: Logger,
): Promise<{ stdout: string; stderr: string }> {
const command = `pdftocairo -jpeg -r 150 "${filePath}" "${outputFilePrefix}"`;
logger.info(`Executing PDF conversion command`);
logger.debug({ command });
try {
const { stdout, stderr } = await this.exec(command);
Eif (stdout) logger.debug({ stdout }, `[Worker] pdftocairo stdout for ${filePath}:`);
Iif (stderr) logger.warn({ stderr }, `[Worker] pdftocairo stderr for ${filePath}:`);
return { stdout, stderr };
} catch (error) {
const execError = error as Error & { stderr?: string };
const errorMessage = `The pdftocairo command failed for file: ${filePath}.`;
logger.error({ err: execError, stderr: execError.stderr }, errorMessage);
throw new PdfConversionError(errorMessage, execError.stderr);
}
}
/**
* Scans the output directory for generated JPEG images and returns their paths.
*/
private async _collectGeneratedImages(
outputDir: string,
outputFilePrefix: string,
logger: Logger,
): Promise<string[]> {
logger.debug(`[Worker] Reading contents of output directory: ${outputDir}`);
const filesInDir = await this.fs.readdir(outputDir, { withFileTypes: true });
logger.debug(`[Worker] Found ${filesInDir.length} total entries in output directory.`);
const generatedImages = filesInDir
.filter((f) => f.name.startsWith(path.basename(outputFilePrefix)) && f.name.endsWith('.jpg'))
.sort((a, b) => a.name.localeCompare(b.name, undefined, { numeric: true }));
logger.debug(
{ imageNames: generatedImages.map((f) => f.name) },
`Filtered down to ${generatedImages.length} generated JPGs.`,
);
return generatedImages.map((img) => path.join(outputDir, img.name));
}
/**
* Converts a PDF file to a series of JPEG images using an external tool.
*/
private async _convertPdfToImages(
filePath: string,
job: Job<FlyerJobData>,
logger: Logger,
): Promise<string[]> {
logger.info(`Starting PDF conversion for: ${filePath}`);
const outputDir = path.dirname(filePath);
const outputFilePrefix = path.join(outputDir, path.basename(filePath, '.pdf'));
logger.debug({ outputDir, outputFilePrefix }, `PDF output details`);
const { stderr } = await this._executePdfConversion(filePath, outputFilePrefix, logger);
const imagePaths = await this._collectGeneratedImages(outputDir, outputFilePrefix, logger);
if (imagePaths.length === 0) {
const errorMessage = `PDF conversion resulted in 0 images for file: ${filePath}. The PDF might be blank or corrupt.`;
logger.error({ stderr }, `PdfConversionError: ${errorMessage}`);
throw new PdfConversionError(errorMessage, stderr);
}
return imagePaths;
}
/**
* Processes a JPEG image to strip EXIF data by re-saving it.
* This ensures user privacy and metadata consistency.
* @returns The path to the newly created, processed JPEG file.
*/
private async _stripExifDataFromJpeg(filePath: string, logger: Logger): Promise<string> {
const outputDir = path.dirname(filePath);
const originalFileName = path.parse(path.basename(filePath)).name;
// Suffix to avoid overwriting, and keep extension.
const newFileName = `${originalFileName}-processed.jpeg`;
const outputPath = path.join(outputDir, newFileName);
logger.info({ from: filePath, to: outputPath }, 'Processing JPEG to strip EXIF data.');
try {
// By default, sharp strips metadata when re-saving.
// We also apply a reasonable quality setting for web optimization.
await sharp(filePath).jpeg({ quality: 90 }).toFile(outputPath);
return outputPath;
} catch (error) {
logger.error({ err: error, filePath }, 'Failed to process JPEG with sharp.');
throw new ImageConversionError(`JPEG processing failed for ${path.basename(filePath)}.`);
}
}
/**
* Processes a PNG image to strip metadata by re-saving it.
* @returns The path to the newly created, processed PNG file.
*/
private async _stripMetadataFromPng(filePath: string, logger: Logger): Promise<string> {
const outputDir = path.dirname(filePath);
const originalFileName = path.parse(path.basename(filePath)).name;
const newFileName = `${originalFileName}-processed.png`;
const outputPath = path.join(outputDir, newFileName);
logger.info({ from: filePath, to: outputPath }, 'Processing PNG to strip metadata.');
try {
// Re-saving with sharp strips metadata. We also apply a reasonable quality setting.
await sharp(filePath).png({ quality: 90 }).toFile(outputPath);
return outputPath;
} catch (error) {
logger.error({ err: error, filePath }, 'Failed to process PNG with sharp.');
throw new ImageConversionError(`PNG processing failed for ${path.basename(filePath)}.`);
}
}
/**
* Converts an image file (e.g., GIF, TIFF) to a PNG format that the AI can process.
*/
private async _convertImageToPng(filePath: string, logger: Logger): Promise<string> {
const outputDir = path.dirname(filePath);
const originalFileName = path.parse(path.basename(filePath)).name;
const newFileName = `${originalFileName}-converted.png`;
const outputPath = path.join(outputDir, newFileName);
logger.info({ from: filePath, to: outputPath }, 'Converting unsupported image format to PNG.');
try {
await sharp(filePath).png().toFile(outputPath);
return outputPath;
} catch (error) {
logger.error({ err: error, filePath }, 'Failed to convert image to PNG using sharp.');
throw new ImageConversionError(`Image conversion to PNG failed for ${path.basename(filePath)}.`);
}
}
/**
* Handles PDF files by converting them to a series of JPEG images.
*/
private async _handlePdfInput(
filePath: string,
job: Job<FlyerJobData>,
logger: Logger,
): Promise<{ imagePaths: { path: string; mimetype: string }[]; createdImagePaths: string[] }> {
const createdImagePaths = await this._convertPdfToImages(filePath, job, logger);
const imagePaths = createdImagePaths.map((p) => ({ path: p, mimetype: 'image/jpeg' }));
logger.info(`Converted PDF to ${imagePaths.length} images.`);
return { imagePaths, createdImagePaths };
}
/**
* Handles image files that are directly supported by the AI.
*/
private async _handleSupportedImageInput(
filePath: string,
fileExt: string,
logger: Logger,
): Promise<{ imagePaths: { path: string; mimetype: string }[]; createdImagePaths: string[] }> {
// For JPEGs, we will re-process them to strip EXIF data.
if (fileExt === '.jpg' || fileExt === '.jpeg') {
const processedPath = await this._stripExifDataFromJpeg(filePath, logger);
return {
imagePaths: [{ path: processedPath, mimetype: 'image/jpeg' }],
// The original file will be cleaned up by the orchestrator, but we must also track this new file.
createdImagePaths: [processedPath],
};
}
// For PNGs, also re-process to strip metadata.
if (fileExt === '.png') {
const processedPath = await this._stripMetadataFromPng(filePath, logger);
return {
imagePaths: [{ path: processedPath, mimetype: 'image/png' }],
createdImagePaths: [processedPath],
};
}
// For other supported types like WEBP, etc., which are less likely to have problematic EXIF,
// we can process them directly without modification for now.
logger.info(`Processing as a single image file (non-JPEG/PNG): ${filePath}`);
return { imagePaths: [{ path: filePath, mimetype: `image/${fileExt.slice(1)}` }], createdImagePaths: [] };
}
/**
* Handles image files that need to be converted to PNG before AI processing.
*/
private async _handleConvertibleImageInput(
filePath: string,
logger: Logger,
): Promise<{ imagePaths: { path: string; mimetype: string }[]; createdImagePaths: string[] }> {
const createdPngPath = await this._convertImageToPng(filePath, logger);
const imagePaths = [{ path: createdPngPath, mimetype: 'image/png' }];
const createdImagePaths = [createdPngPath];
return { imagePaths, createdImagePaths };
}
/**
* Throws an error for unsupported file types.
*/
private _handleUnsupportedInput(
fileExt: string,
originalFileName: string,
logger: Logger,
): never {
const errorMessage = `Unsupported file type: ${fileExt}. Supported types are PDF, JPG, PNG, WEBP, HEIC, HEIF, GIF, TIFF, SVG, BMP.`;
logger.error({ originalFileName, fileExt }, errorMessage);
throw new UnsupportedFileTypeError(errorMessage);
}
/**
* Prepares the input images for the AI service. If the input is a PDF, it's converted to images.
*/
public async prepareImageInputs(
filePath: string,
job: Job<FlyerJobData>,
logger: Logger,
): Promise<{ imagePaths: { path: string; mimetype: string }[]; createdImagePaths: string[] }> {
console.error(`[WORKER DEBUG] FlyerFileHandler: prepareImageInputs called for ${filePath}`);
const fileExt = path.extname(filePath).toLowerCase();
console.error(`[WORKER DEBUG] FlyerFileHandler: Detected extension: ${fileExt}`);
if (fileExt === '.pdf') {
return this._handlePdfInput(filePath, job, logger);
}
if (SUPPORTED_IMAGE_EXTENSIONS.includes(fileExt)) {
return this._handleSupportedImageInput(filePath, fileExt, logger);
}
if (CONVERTIBLE_IMAGE_EXTENSIONS.includes(fileExt)) {
return this._handleConvertibleImageInput(filePath, logger);
}
return this._handleUnsupportedInput(fileExt, job.data.originalFileName, logger);
}
/**
* Optimizes images for web delivery (compression, resizing).
* This is a distinct processing stage.
*/
public async optimizeImages(
imagePaths: { path: string; mimetype: string }[],
logger: Logger,
): Promise<void> {
logger.info(`Starting image optimization for ${imagePaths.length} images.`);
for (const image of imagePaths) {
const tempPath = `${image.path}.tmp`;
try {
// Optimize: Resize to max width 2000px (preserving aspect ratio) and compress
await sharp(image.path)
.resize({ width: 2000, withoutEnlargement: true })
.jpeg({ quality: 80, mozjpeg: true }) // Use mozjpeg for better compression
.toFile(tempPath);
// Replace the original file with the optimized version
await this.fs.rename(tempPath, image.path);
} catch (error) {
logger.error({ err: error, path: image.path }, 'Failed to optimize image.');
throw new ImageConversionError(`Image optimization failed for ${path.basename(image.path)}.`);
}
}
logger.info('Image optimization complete.');
}
} |