@thecodingwhale/cv-processor
Version:
CV Processor to extract structured data from PDF resumes using TypeScript
107 lines (106 loc) • 4.51 kB
JavaScript
;
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
var ownKeys = function(o) {
ownKeys = Object.getOwnPropertyNames || function (o) {
var ar = [];
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
return ar;
};
return ownKeys(o);
};
return function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
__setModuleDefault(result, mod);
return result;
};
})();
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.convertPdfToTexts = convertPdfToTexts;
exports.convertPdfToImages = convertPdfToImages;
const child_process_1 = require("child_process");
const fs = __importStar(require("fs"));
const os = __importStar(require("os"));
const path = __importStar(require("path"));
const pdf_parse_1 = __importDefault(require("pdf-parse"));
const util_1 = require("util");
const execAsync = (0, util_1.promisify)(child_process_1.exec);
/**
* Converts a PDF file to base64-encoded PNG images using pdftoppm.
* Requires poppler-utils to be installed.
*
* @param pdfPath - The file path of the PDF to convert
* @returns A promise that resolves to an array of base64 image data URLs
*/
async function convertPdfToImages(pdfPath) {
console.log(`[convertPdfToImages] Creating temp directory for PDF images`);
const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pdf-images-'));
console.log(`[convertPdfToImages] Temp directory created: ${tempDir}`);
try {
const command = `pdftoppm -png -r 200 "${pdfPath}" "${path.join(tempDir, 'page')}"`;
console.log(`[convertPdfToImages] Executing command: ${command}`);
await execAsync(command);
const files = fs
.readdirSync(tempDir)
.filter((file) => file.endsWith('.png'));
console.log(`[convertPdfToImages] Found ${files.length} image files: ${files.join(', ')}`);
const sortedFiles = files.map((file) => path.join(tempDir, file)).sort();
console.log(`[convertPdfToImages] Sorted file paths: ${sortedFiles.join(', ')}`);
const imageUrls = sortedFiles.map((file) => {
const data = fs.readFileSync(file);
const base64 = data.toString('base64');
console.log(`[convertPdfToImages] Converted image ${file}, size: ${base64.length} chars`);
return `data:image/png;base64,${base64}`;
});
console.log(`[convertPdfToImages] Returning ${imageUrls.length} base64 image URLs`);
return imageUrls;
}
catch (error) {
console.error('[convertPdfToImages] Error converting PDF to images:', error);
throw error;
}
}
/**
* Convert PDF to text using pdf-parse
* @param pdfPath Path to the PDF file
* @returns Array of text content from each page
*/
async function convertPdfToTexts(pdfPath) {
try {
// Read the PDF file
const dataBuffer = fs.readFileSync(pdfPath);
// Parse the PDF
const data = await (0, pdf_parse_1.default)(dataBuffer);
// Split the text into pages
// Note: pdf-parse doesn't provide direct page separation
// We'll use a simple heuristic to split pages based on page numbers
const pages = data.text
.split(/\n\s*\d+\s*\n/)
.filter((page) => page.trim().length > 0);
return pages;
}
catch (error) {
console.error('Error converting PDF to text:', error);
throw error;
}
}