优化后端

2026-09-11 17:56:56 +08:00
parent 7eed11b774
commit 812e67422d
7299 changed files with 1744959 additions and 112 deletions
@@ -0,0 +1,29 @@
+<!DOCTYPE HTML>
+<html>
+  <head>
+    <script src="/dist/tesseract.min.js"></script>
+  </head>
+  <body>
+    <input type="file" id="uploader" multiple>
+    <script type="module">
+
+      // A worker is created once and used every time a user uploads a new file.  
+      const worker = await Tesseract.createWorker("eng", 1, {
+          corePath: '../../node_modules/tesseract.js-core',
+          workerPath: "/dist/worker.min.js",
+          logger: function(m){console.log(m);}
+        });
+
+      const recognize = async function(evt){
+        const files = evt.target.files;
+        
+        for (let i=0; i<files.length; i++) {
+          const ret = await worker.recognize(files[i]);
+          console.log(ret.data.text);
+        }
+      }
+      const elm = document.getElementById('uploader');
+      elm.addEventListener('change', recognize);
+    </script>
+  </body>
+</html>
@@ -0,0 +1,47 @@
+<!DOCTYPE HTML>
+<html>
+  <head>
+    <script src="/dist/tesseract.min.js"></script>
+  </head>
+  <body>
+    <input type="file" id="uploader" multiple>
+    <script type="module">
+
+      // This example builds on "basic-efficient.html".
+      // Rather than using a single worker, a scheduler manages a pool of multiple workers. 
+      // While performance is similar for a single file, this parallel processing results in significantly
+      // faster speeds when used with multiple files.
+
+      const scheduler = Tesseract.createScheduler();
+
+      // Creates worker and adds to scheduler
+      const workerGen = async () => {
+        const worker = await Tesseract.createWorker("eng", 1, {
+          corePath: '../../node_modules/tesseract.js-core',
+          workerPath: "/dist/worker.min.js",
+          logger: function(m){console.log(m);}
+        });
+        scheduler.addWorker(worker);
+      }
+
+      const workerN = 4;
+      (async () => {
+        const resArr = Array(workerN);
+        for (let i=0; i<workerN; i++) {
+          resArr[i] = await workerGen();
+        }
+      })();
+
+      const recognize = async function(evt){
+        const files = evt.target.files;
+
+        for (let i=0; i<files.length; i++) {
+          scheduler.addJob('recognize', files[i]).then((x) => console.log(x.data.text))
+        }
+      }
+
+      const elm = document.getElementById('uploader');
+      elm.addEventListener('change', recognize);
+    </script>
+  </body>
+</html>
@@ -0,0 +1,52 @@
+<html>
+  <head>
+    <script src="/dist/tesseract.min.js"></script>
+  </head>
+  <body>
+    <div>
+      <input type="file" id="uploader">
+      <button id="download-pdf" disabled="true">Download PDF</button>
+    </div>
+    <textarea id="board" readonly rows="8" cols="80">Upload an image file</textarea>
+    <script type="module">
+      const { createWorker } = Tesseract;
+      const worker = await createWorker("eng", 1, {
+        corePath: '/node_modules/tesseract.js-core',
+        workerPath: "/dist/worker.min.js",
+        logger: m => console.log(m),
+      });
+      const uploader = document.getElementById('uploader');
+      const dlBtn = document.getElementById('download-pdf');
+      let pdf;
+      const recognize = async ({ target: { files }  }) => {
+        const res = await worker.recognize(files[0],{pdfTitle: "Example PDF"},{pdf: true});
+        pdf = res.data.pdf;
+        const text = res.data.text;
+        const board = document.getElementById('board');
+        board.value = text;
+        dlBtn.disabled = false;
+      };
+      const downloadPDF = async () => {
+        const filename = 'tesseract-ocr-result.pdf';
+        const blob = new Blob([new Uint8Array(pdf)], { type: 'application/pdf' });
+        if (navigator.msSaveBlob) {
+          // IE 10+
+          navigator.msSaveBlob(blob, filename);
+        } else {
+          const link = document.createElement('a');
+          if (link.download !== undefined) {
+            const url = URL.createObjectURL(blob);
+            link.setAttribute('href', url);
+            link.setAttribute('download', filename);
+            link.style.visibility = 'hidden';
+            document.body.appendChild(link);
+            link.click();
+            document.body.removeChild(link);
+          }
+        }
+      };
+      uploader.addEventListener('change', recognize);
+      dlBtn.addEventListener('click', downloadPDF);
+    </script>
+  </body>
+</html>
@@ -0,0 +1,55 @@
+<html>
+
+<head>
+  <script src="/dist/tesseract.min.js"></script>
+  <style>
+    .column {
+  float: left;
+  width: 20%;
+  padding: 5px;
+}
+
+  </style>
+</head>
+
+<body>
+  <input type="file" id="uploader">
+
+  <div class="row">
+    <div class="column">
+      <p>Input Image</p>
+      <img id="imgInput" style="max-width:500px;">
+    </div>
+    <div class="column">
+      <p>Rotated, Original Color</p>
+      <img id="imgOriginal" style="max-width:500px;">
+    </div>
+    <div class="column">
+      <p>Rotated, Grey</p>
+      <img id="imgGrey" style="max-width:500px;">
+    </div>
+    <div class="column">
+      <p>Rotated, Binary</p>
+      <img id="imgBinary" style="max-width:500px;">
+    </div>
+  </div>
+
+  <script>
+    const recognize = async ({ target: { files } }) => {
+      document.getElementById("imgInput").src = URL.createObjectURL(files[0]);
+      const worker = await Tesseract.createWorker("eng", 1, {
+        // corePath: '/tesseract-core-simd.wasm.js',
+        workerPath: "/dist/worker.min.js"
+      });
+      const ret = await worker.recognize(files[0], {rotateAuto: true}, {imageColor: true, imageGrey: true, imageBinary: true});
+      document.getElementById("imgOriginal").src = ret.data.imageColor;
+      document.getElementById("imgGrey").src = ret.data.imageGrey;
+      document.getElementById("imgBinary").src = ret.data.imageBinary;
+
+    }
+    const elm = document.getElementById('uploader');
+    elm.addEventListener('change', recognize);
+  </script>
+</body>
+
+</html>
@@ -0,0 +1,21 @@
+#!/usr/bin/env node
+
+'use strict';
+
+const path = require('path');
+const fs = require('fs');
+const { createWorker } = require('../..');
+
+const [,, imagePath] = process.argv;
+const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
+
+console.log(`Recognizing ${image}`);
+
+(async () => {
+  const worker = await createWorker();
+  const { data: { text, pdf } } = await worker.recognize(image, { pdfTitle: 'Example PDF' }, { pdf: true });
+  console.log(text);
+  fs.writeFileSync('tesseract-ocr-result.pdf', Buffer.from(pdf));
+  console.log('Generate PDF: tesseract-ocr-result.pdf');
+  await worker.terminate();
+})();
@@ -0,0 +1,37 @@
+#!/usr/bin/env node
+
+'use strict';
+
+const path = require('path');
+const fs = require('fs');
+const { createWorker } = require('../..');
+
+const [,, imagePath] = process.argv;
+const image = path.resolve(__dirname, (imagePath || '../data/meditations.jpg'));
+
+console.log(`Recognizing ${image}`);
+
+// Tesseract.js returns images (imageColor, imageGrey, imageBinary) as strings
+// to be used as source tags.
+// This function converts to Uint8Array data for saving to disk.
+const convertImage = (imageSrc) => {
+  const data = atob(imageSrc.split(',')[1])
+    .split('')
+    .map((c) => c.charCodeAt(0));
+
+  return new Uint8Array(data);
+};
+
+(async () => {
+  const worker = await createWorker();
+  const { data: { imageColor, imageGrey, imageBinary } } = await worker.recognize(image,
+    { rotateAuto: true }, { imageColor: true, imageGrey: true, imageBinary: true });
+
+  console.log('Saving intermediate images: imageColor.png, imageGrey.png, imageBinary.png');
+
+  fs.writeFileSync('imageColor.png', convertImage(imageColor));
+  fs.writeFileSync('imageGrey.png', convertImage(imageGrey));
+  fs.writeFileSync('imageBinary.png', convertImage(imageBinary));
+
+  await worker.terminate();
+})();
@@ -0,0 +1,20 @@
+#!/usr/bin/env node
+
+'use strict';
+
+const path = require('path');
+const { createWorker } = require('../..');
+
+const [,, imagePath] = process.argv;
+const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
+
+console.log(`Recognizing ${image}`);
+
+(async () => {
+  const worker = await createWorker('eng', 1, {
+    logger: (m) => console.log(m),
+  });
+  const { data: { text } } = await worker.recognize(image);
+  console.log(text);
+  await worker.terminate();
+})();
@@ -0,0 +1,40 @@
+'use strict';
+
+const path = require('path');
+const { createWorker, createScheduler } = require('../..');
+
+const [,, imagePath] = process.argv;
+
+// Note: This example recognizes the same image 4 times in parallel
+// to show how schedulers can be used to speed up bulk jobs.
+// In actual use you would (obviously) not want to run multiple identical jobs.
+
+const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
+const imageArr = [image, image, image, image];
+
+const scheduler = createScheduler();
+
+// Creates worker and adds to scheduler
+const workerGen = async () => {
+  const worker = await createWorker('eng', 1, { cachePath: '.' });
+  scheduler.addWorker(worker);
+};
+
+const workerN = 4;
+(async () => {
+  const resArr = Array(workerN);
+  for (let i = 0; i < workerN; i++) {
+    resArr[i] = workerGen();
+  }
+  await Promise.all(resArr);
+
+  const resArr2 = Array(imageArr.length);
+
+  for (let i = 0; i < imageArr.length; i++) {
+    resArr2[i] = scheduler.addJob('recognize', image).then((x) => console.log(x.data.text));
+  }
+
+  await Promise.all(resArr2);
+
+  await scheduler.terminate(); // It also terminates all workers.
+})();