ocr-document-classification - npm Package Compare versions

Comparing version 1.2.8 to 1.2.9

dist/index.js

@@ -1,49 +0,31 @@
-var __defProp = Object.defineProperty;
-var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
-var __getOwnPropNames = Object.getOwnPropertyNames;
-var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __esm = (fn, res) => function __init() {
-  return fn && (res = (0, fn[__getOwnPropNames(fn)[0]])(fn = 0)), res;
-};
-var __export = (target, all) => {
-  for (var name in all)
-    __defProp(target, name, { get: all[name], enumerable: true });
-};
-var __copyProps = (to, from, except, desc) => {
-  if (from && typeof from === "object" || typeof from === "function") {
-    for (let key of __getOwnPropNames(from))
-      if (!__hasOwnProp.call(to, key) && key !== except)
-        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
-  }
-  return to;
-};
-var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+// src/functions.ts
+import { stringSimilarity } from "string-similarity-js";
+import * as Tesseract from "tesseract.js";
 
-// src/convert.mjs
-var convert_exports = {};
-__export(convert_exports, {
-  convert: () => convert
-});
+// src/convert.js
+import * as pdfjsLib from "pdfjs-dist";
+pdfjsLib.GlobalWorkerOptions.workerSrc = "//mozilla.github.io/pdf.js/build/pdf.worker.js";
 async function convert(pdfPath) {
-  pdfjsLib.GlobalWorkerOptions.workerSrc = "//mozilla.github.io/pdf.js/build/pdf.worker.js";
-  const doc = await pdfjsLib.getDocument(pdfPath);
-  const page = await doc.getPage(1);
-  const viewport = page.getViewport({ scale: 1.5 });
-  const canvas = document.createElement("canvas");
-  const context = canvas.getContext("2d");
-  canvas.height = viewport.height;
-  canvas.width = viewport.width;
-  await page.render({ canvasContext: context, viewport }).promise;
-  const buffer = canvas.toDataURL("image/png");
-  return buffer;
+  try {
+    const doc = await pdfjsLib.getDocument(pdfPath).promise;
+    const page = await doc.getPage(1);
+    const viewport = page.getViewport({ scale: 1.5 });
+    const canvas = document.createElement("canvas");
+    const context = canvas.getContext("2d");
+    canvas.height = viewport.height;
+    canvas.width = viewport.width;
+    const renderContext = {
+      canvasContext: context,
+      viewport
+    };
+    await page.render(renderContext).promise;
+    const buffer = canvas.toDataURL("image/png");
+    return buffer;
+  } catch (error) {
+    console.error("Error processing PDF:", error);
+    throw error;
+  }
 }
-var init_convert = __esm({
-  "src/convert.mjs"() {
-    "use strict";
-  }
-});
 
 // src/functions.ts
-import { stringSimilarity } from "string-similarity-js";
-import * as Tesseract from "tesseract.js";
 function findTargetWords(documentText, targetWords, threshold = 0.75) {
@@ -85,6 +67,5 @@ const foundTargetWords = [];
   };
-  const { convert: convert2 } = (init_convert(), __toCommonJS(convert_exports));
   if (file.type === "application/pdf") {
     const pdfPath = URL.createObjectURL(file);
-    file = await convert2(pdfPath);
+    file = await convert(pdfPath);
   }
@@ -91,0 +72,0 @@ let progress = 0;

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.2.8",
+  "version": "1.2.9",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -29,2 +29,3 @@ "main": "./dist/index.cjs",
   "dependencies": {
+    "pdfjs-dist": "^4.4.168",
     "string-similarity-js": "^2.1.4",
@@ -31,0 +32,0 @@ "tesseract.js": "^5.1.0",

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Worsened metrics

Total package byte prevSize

30237

decreased by-1.48%

Dependency count

4

increased by33.33%

Lines of code

295

decreased by-6.65%

Dependency changes

• + Addedpdfjs-dist@^4.4.168

• + Addedbase64-js@1.5.1(transitive)

• + Addedbl@4.1.0(transitive)

• + Addedbuffer@5.7.1(transitive)

• + Addedcanvas@3.0.0-rc2(transitive)

• + Addedchownr@1.1.4(transitive)

• + Addeddecompress-response@4.2.16.0.0(transitive)

• + Addeddeep-extend@0.6.0(transitive)

• + Addeddetect-libc@2.0.3(transitive)

• + Addedend-of-stream@1.4.4(transitive)

• + Addedexpand-template@2.0.3(transitive)

• + Addedfs-constants@1.0.0(transitive)

• + Addedgithub-from-package@0.0.0(transitive)

• + Addedieee754@1.2.1(transitive)

• + Addedinherits@2.0.4(transitive)

• + Addedini@1.3.8(transitive)

• + Addedmimic-response@2.1.03.1.0(transitive)

• + Addedminimist@1.2.8(transitive)

• + Addedmkdirp-classic@0.5.3(transitive)

• + Addednapi-build-utils@1.0.2(transitive)

• + Addednode-abi@3.71.0(transitive)

• + Addednode-addon-api@7.1.1(transitive)

• + Addedonce@1.4.0(transitive)

• + Addedpath2d@0.2.2(transitive)

• + Addedpdfjs-dist@4.8.69(transitive)

• + Addedprebuild-install@7.1.2(transitive)

• + Addedpump@3.0.2(transitive)

• + Addedrc@1.2.8(transitive)

• + Addedreadable-stream@3.6.2(transitive)

• + Addedsafe-buffer@5.2.1(transitive)

• + Addedsemver@7.6.3(transitive)

• + Addedsimple-concat@1.0.1(transitive)

• + Addedsimple-get@3.1.14.0.1(transitive)

• + Addedstring_decoder@1.3.0(transitive)

• + Addedstrip-json-comments@2.0.1(transitive)

• + Addedtar-fs@2.1.1(transitive)

• + Addedtar-stream@2.2.0(transitive)

• + Addedtunnel-agent@0.6.0(transitive)

• + Addedutil-deprecate@1.0.2(transitive)

• + Addedwrappy@1.0.2(transitive)