PHP环境下海量PDF文本快速检索优化策略

composer require spatie/pdf-to-text

<?php
require 'vendor/autoload.php';

use Spatie\PdfToText\Pdf;

// 假设你的PDF文件路径存储在数据库中
$pdfFilePath = '/path/to/your/document.pdf';
$documentId = 123; // 关联的文档ID

try {
    // 实例化Pdf类，并指定pdftotext的路径（如果不在系统PATH中）
    $pdf = new Pdf('/usr/bin/pdftotext'); // 根据你的pdftotext安装路径调整

    // 从PDF中提取文本
    $text = $pdf->setPdf($pdfFilePath)->text();

    echo "文档ID: " . $documentId . "\n";
    echo "提取文本成功，准备存储...\n";
    // 在此处将 $text 存储到数据库中，关联 $documentId
    // ...
} catch (Exception $e) {
    echo "提取PDF文本失败: " . $e->getMessage() . "\n";
    // 记录错误或处理异常
}
?>

CREATE TABLE `document_texts` (
    `id` INT AUTO_INCREMENT PRIMARY KEY,
    `document_id` INT NOT NULL,           -- 关联到原始文档的ID
    `extracted_text` LONGTEXT NOT NULL,   -- 存储提取的PDF文本
    `created_at` TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
    `updated_at` TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
    INDEX `idx_document_id` (`document_id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;

<?php
// ... 假设 $documentId 和 $extractedText 已获取

$pdo = new PDO('mysql:host=localhost;dbname=your_database', 'username', 'password');
$pdo->setAttribute(PDO::ATTR_ERRMODE, PDO::ERRMODE_EXCEPTION);

$stmt = $pdo->prepare("INSERT INTO document_texts (document_id, extracted_text) VALUES (:document_id, :extracted_text)");
$stmt->bindParam(':document_id', $documentId);
$stmt->bindParam(':extracted_text', $extractedText);

try {
    $stmt->execute();
    echo "文本已成功存储到数据库。\n";
} catch (PDOException $e) {
    echo "数据库插入失败: " . $e->getMessage() . "\n";
}
?>

ALTER TABLE `document_texts` ADD FULLTEXT `ft_extracted_text` (`extracted_text`);

<?php
// ... 假设 $pdo 连接已建立

$searchTerm = '你的搜索关键词'; // 用户输入的关键词

// 构建查询，使用 MATCH AGAINST
// 注意：MATCH AGAINST 对搜索词有最短长度限制，默认为4个字符
$query = "SELECT document_id FROM document_texts WHERE MATCH(extracted_text) AGAINST(:searchTerm IN BOOLEAN MODE)";

$stmt = $pdo->prepare($query);
$stmt->bindValue(':searchTerm', $searchTerm);

try {
    $stmt->execute();
    $results = $stmt->fetchAll(PDO::FETCH_ASSOC);

    if ($results) {
        echo "找到匹配的文档ID:\n";
        foreach ($results as $row) {
            echo " - " . $row['document_id'] . "\n";
        }
    } else {
        echo "未找到匹配的文档。\n";
    }
} catch (PDOException $e) {
    echo "搜索查询失败: " . $e->getMessage() . "\n";
}
?>