nano-ai-pdf/dist/pdf-extractor.js

This package helps you summarize pdfs using Gemini nano on edge or on browser, making it compliant safe, faster and free

var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
import pdfToText from "react-pdftotext";
import { PdfSummarizerError } from "./types";
/**
 * Extracts text content from a PDF file
 *
 * @param file - The PDF file to extract text from
 * @param minTextLength - Minimum required text length (default: 100)
 * @returns Promise resolving to the extracted text
 * @throws PdfSummarizerError if extraction fails or text is insufficient
 */
export function extractTextFromPdf(file_1) {
    return __awaiter(this, arguments, void 0, function* (file, minTextLength = 100) {
        try {
            console.log(`📖 Starting PDF text extraction for: ${file.name}`);
            console.log(`📄 File size: ${(file.size / 1024 / 1024).toFixed(2)} MB`);
            // Extract text using react-pdftotext
            const rawText = yield pdfToText(file);
            if (!rawText || typeof rawText !== "string") {
                throw new PdfSummarizerError("PDF text extraction returned no content", "EXTRACTION_EMPTY");
            }
            // Clean and normalize the extracted text
            const cleanedText = rawText
                .replace(/\s+/g, " ")
                .replace(/\n\s*\n/g, "\n\n")
                .trim();
            console.log(`✅ Text extraction completed: ${cleanedText.length} characters`);
            // Validate minimum text length
            if (cleanedText.length < minTextLength) {
                throw new PdfSummarizerError(`PDF contains insufficient text content (${cleanedText.length} chars, minimum ${minTextLength} required)`, "INSUFFICIENT_TEXT");
            }
            return cleanedText;
        }
        catch (error) {
            const errorMessage = error instanceof Error ? error.message : "Unknown error";
            console.error(`❌ PDF text extraction failed: ${errorMessage}`);
            if (error instanceof PdfSummarizerError) {
                throw error;
            }
            throw new PdfSummarizerError(`Failed to extract text from PDF: ${errorMessage}`, "EXTRACTION_FAILED");
        }
    });
}
/**
 * Validates a PDF file before processing
 *
 * @param file - The file to validate
 * @param maxFileSize - Maximum allowed file size in bytes
 * @throws PdfSummarizerError if validation fails
 */
export function validatePdfFile(file, maxFileSize = 10 * 1024 * 1024) {
    console.log(`🔍 Validating PDF file: ${file.name}`);
    // Check if file exists
    if (!file) {
        throw new PdfSummarizerError("No file provided", "NO_FILE");
    }
    // Check file type
    if (file.type !== "application/pdf") {
        throw new PdfSummarizerError(`Invalid file type: ${file.type}. Only PDF files are supported.`, "INVALID_FILE_TYPE");
    }
    // Check file size
    if (file.size > maxFileSize) {
        throw new PdfSummarizerError(`File size (${(file.size / 1024 / 1024).toFixed(2)} MB) exceeds maximum allowed size (${(maxFileSize /
            1024 /
            1024).toFixed(2)} MB)`, "FILE_TOO_LARGE");
    }
    // Check for empty file
    if (file.size === 0) {
        throw new PdfSummarizerError("PDF file is empty", "EMPTY_FILE");
    }
    console.log(`✅ PDF file validation passed`);
}
//# sourceMappingURL=pdf-extractor.js.map