Update pdfjs and convert to pdfExtract esm

.github/workflows/nodejs.yml

@@ -2,26 +2,26 @@ name: test
 
 on:
   push:
-    branches: [ main ]
+    branches: [main]
   pull_request:
-    branches: [ main ]
+    branches: [main]
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
 
     strategy:
       matrix:
-        node-version: [12.x, 13.x, 14.x, 15.x, 16.x, 17.x]
+        node-version:
+          [12.x, 13.x, 14.x, 15.x, 16.x, 17.x, 18.x, 19.x, 20.x, 21.x]
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Use Node.js ${{ matrix.node-version }}
-      uses: actions/setup-node@v1
-      with:
-        node-version: ${{ matrix.node-version }}
-    - run: npm ci
-    - run: npm test
-      env:
-        CI: true
+      - uses: actions/checkout@v2
+      - name: Use Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v1
+        with:
+          node-version: ${{ matrix.node-version }}
+      - run: npm ci
+      - run: npm test
+        env:
+          CI: true

README.md

@@ -15,26 +15,44 @@ Note: NO OCR!
 [![NPM](https://nodei.co/npm/pdf.js-extract.png?downloads=true&downloadRank=true&stars=true)](https://nodei.co/npm/pdf.js-extract/)
 
 ![test](https://github.com/ffalt/pdf.js-extract/workflows/test/badge.svg)
-[![license](https://img.shields.io/npm/l/pdf.js-extract.svg)](http://opensource.org/licenses/MIT) 
+[![license](https://img.shields.io/npm/l/pdf.js-extract.svg)](http://opensource.org/licenses/MIT)
 
 ## Example Usage
 
+### Esm version >= 1.0.0
+
+javascript async with promise
+
+```javascript
+import { PDFExtract } from "pdf.js-extract";
+const pdfExtract = new PDFExtract();
+const options = {}; /* see below */
+pdfExtract
+  .extract("example.pdf", options)
+  .then((data) => console.log(data))
+  .catch((err) => console.log(err));
+```
+
+### Commonjs version < 1.0.0
+
 javascript async with callback
+
 ```javascript
-const PDFExtract = require('pdf.js-extract').PDFExtract;
+const PDFExtract = require("pdf.js-extract").PDFExtract;
 const pdfExtract = new PDFExtract();
 const options = {}; /* see below */
-pdfExtract.extract('test.pdf', options, (err, data) => {
+pdfExtract.extract("example.pdf", options, (err, data) => {
   if (err) return console.log(err);
   console.log(data);
 });
 ```
 
 javascript async with callback using buffer
+
 ```javascript
-const PDFExtract = require('pdf.js-extract').PDFExtract;
+const PDFExtract = require("pdf.js-extract").PDFExtract;
 const pdfExtract = new PDFExtract();
-const fs = require('fs');
+const fs = require("fs");
 const buffer = fs.readFileSync("./example.pdf");
 const options = {}; /* see below */
 pdfExtract.extractBuffer(buffer, options, (err, data) => {
@@ -43,17 +61,22 @@ pdfExtract.extractBuffer(buffer, options, (err, data) => {
 });
 ```
 
+### Typescript
+
 typescript async with promise
+
 ```typescript
-import {PDFExtract, PDFExtractOptions} from 'pdf.js-extract';
+import { PDFExtract, PDFExtractOptions } from "pdf.js-extract";
 const pdfExtract = new PDFExtract();
 const options: PDFExtractOptions = {}; /* see below */
-pdfExtract.extract('test.pdf', options)
-  .then(data => console.log(data))
-  .catch(err=> console.log(err));
+pdfExtract
+  .extract("example.pdf", options)
+  .then((data) => console.log(data))
+  .catch((err) => console.log(err));
 ```
 
 ## Options
+
 ```typescript
 export interface PDFExtractOptions {
   firstPage?: number; // default:`1` - start extract at page nr
@@ -73,14 +96,23 @@ Example Output
   "meta": {
     "info": {
       "PDFFormatVersion": "1.7",
+      "Language": null,
+      "EncryptFilterName": null,
+      "IsLinearized": false,
       "IsAcroFormPresent": false,
+      "IsXFAPresent": false,
       "IsCollectionPresent": false,
-      "IsLinearized": true,
-      "IsXFAPresent": false
+      "IsSignaturesPresent": false,
+      "Author": "someone",
+      "CreationDate": "D:20000629102108+11'00'",
+      "Creator": "Microsoft Word 8.0",
+      "ModDate": "D:20131028152413-04'00'",
+      "Producer": "Acrobat Distiller 4.0 for Windows",
+      "Title": "This is a test PDF file"
     },
     "metadata": {
       "dc:format": "application/pdf",
-      "dc:creator": "someone",
+      "dc:creator": ["someone"],
       "dc:title": "This is a hello world PDF file",
       "xmp:createdate": "2000-06-29T10:21:08+11:00",
       "xmp:creatortool": "Microsoft Word 8.0",
@@ -102,9 +134,7 @@ Example Output
         "width": 200,
         "height": 200
       },
-      "links": [
-        "https://github.com"
-      ],
+      "links": ["https://github.com"],
       "content": [
         {
           "x": 70,
@@ -113,7 +143,7 @@ Example Output
           "dir": "ltr",
           "width": 64.656,
           "height": 12,
-          "fontName": "Times"
+          "fontName": "g_d0_f1"
         }
       ]
     }

example/encrypted-output.json

@@ -2,22 +2,24 @@
 	"meta": {
 		"info": {
 			"PDFFormatVersion": "1.7",
-			"IsAcroFormPresent": false,
-			"IsCollectionPresent": false,
+			"Language": "en-GB",
+			"EncryptFilterName": "Standard",
 			"IsLinearized": false,
+			"IsAcroFormPresent": false,
 			"IsXFAPresent": false,
+			"IsCollectionPresent": false,
 			"IsSignaturesPresent": false,
-			"Language": "en-GB",
 			"Author": "Ilan Copelyn\u0000",
 			"Creator": "Microsoft® Word 2016\u0000",
-			"EncryptFilterName": "Standard",
-			"Producer": "Microsoft® Word 2016\u0000",
 			"CreationDate": "D:20180201124627+02'00'",
-			"ModDate": "D:20180201124627+02'00'"
+			"ModDate": "D:20180201124627+02'00'",
+			"Producer": "Microsoft® Word 2016\u0000"
 		},
 		"metadata": {
 			"pdf:producer": "Microsoft® Word 2016",
-			"dc:creator": ["Ilan Copelyn"],
+			"dc:creator": [
+				"Ilan Copelyn"
+			],
 			"xmp:creatortool": "Microsoft® Word 2016",
 			"xmp:createdate": "2018-02-01T12:46:27+02:00",
 			"xmp:modifydate": "2018-02-01T12:46:27+02:00",
@@ -43,7 +45,7 @@
 					"y": 82.43999999999994,
 					"str": "Hello I",
 					"dir": "ltr",
-					"width": 28.549439999999997,
+					"width": 28.549440000000004,
 					"height": 11.04,
 					"fontName": "g_d0_f1"
 				},
@@ -61,7 +63,7 @@
 					"y": 82.43999999999994,
 					"str": "m an e",
 					"dir": "ltr",
-					"width": 30.326880000000003,
+					"width": 30.326879999999996,
 					"height": 11.04,
 					"fontName": "g_d0_f1"
 				},
@@ -70,7 +72,7 @@
 					"y": 82.43999999999994,
 					"str": "ncr",
 					"dir": "ltr",
-					"width": 14.285759999999998,
+					"width": 14.285760000000002,
 					"height": 11.04,
 					"fontName": "g_d0_f1"
 				},
@@ -79,25 +81,12 @@
 					"y": 82.43999999999994,
 					"str": "ypted pdf",
 					"dir": "ltr",
-					"width": 43.07807999999999,
-					"height": 11.04,
-					"fontName": "g_d0_f1"
-				},
-				{
-					"x": 190.85,
-					"y": 82.43999999999994,
-					"str": " ",
-					"dir": "ltr",
-					"width": 2.49504,
+					"width": 43.07807999999997,
 					"height": 11.04,
 					"fontName": "g_d0_f1"
 				}
 			]
 		}
 	],
-	"pdfInfo": {
-		"numPages": 1,
-		"fingerprint": "2e22bde07d96d0408524c26eeecd3483"
-	},
 	"filename": "./encrypted.pdf"
-}
+}

example/encrypted-output.txt

@@ -1 +1 @@
-Hello I’m an encrypted pdf 
+Hello I’m an encrypted pdf

example/encrypted.mjs

@@ -0,0 +1,27 @@
+import { writeFileSync } from "fs";
+import { PDFExtract } from "../lib/index.mjs";
+
+const pdfExtract = new PDFExtract();
+pdfExtract.extract(
+  "./encrypted.pdf",
+  { password: "password" },
+  function (err, data) {
+    if (err) {
+      // eslint-disable-next-line no-console
+      return console.error(err);
+    }
+
+    writeFileSync("./encrypted-output.json", JSON.stringify(data, null, "\t"));
+    // eslint-disable-next-line no-console
+    console.log(JSON.stringify(data, null, "\t"));
+
+    const lines = PDFExtract.utils.pageToLines(data.pages[0], 2);
+    const rows = PDFExtract.utils.extractTextRows(lines);
+    const text = rows
+      .map(function (row) {
+        return row.join("");
+      })
+      .join("\n");
+    writeFileSync("./encrypted-output.txt", text);
+  },
+);

example/example-async.mjs

@@ -0,0 +1,13 @@
+import { PDFExtract } from "../lib/index.mjs";
+
+async function run() {
+  const pdfExtract = new PDFExtract();
+  const data = await pdfExtract.extract("./example.pdf", {} /* options*/);
+  // eslint-disable-next-line no-console
+  console.log(JSON.stringify(data, null, "\t"));
+}
+
+run().catch((e) => {
+  // eslint-disable-next-line no-console
+  console.error(e);
+});

example/example-buffer.mjs

@@ -0,0 +1,18 @@
+import { readFileSync } from "fs";
+import { deepEqual } from "assert";
+import { PDFExtract } from "../lib/index.mjs";
+
+const pdfExtract = new PDFExtract();
+
+const json = JSON.parse(readFileSync("./example-output.json", "utf8"));
+const buffer = readFileSync("./example.pdf");
+
+pdfExtract.extractBuffer(buffer, {}, (err, data) => {
+  if (err) {
+    // eslint-disable-next-line no-console
+    return console.error(err);
+  }
+
+  deepEqual(data.meta, json.meta);
+  deepEqual(data.pages, json.pages);
+});

example/example-cmap-output.json

@@ -2,13 +2,13 @@
 	"meta": {
 		"info": {
 			"PDFFormatVersion": "1.3",
+			"Language": null,
+			"EncryptFilterName": null,
 			"IsLinearized": false,
 			"IsAcroFormPresent": false,
-			"IsCollectionPresent": false,
 			"IsXFAPresent": false,
+			"IsCollectionPresent": false,
 			"IsSignaturesPresent": false,
-			"EncryptFilterName": null,
-			"Language": null,
 			"Producer": "FPDF 1.52",
 			"CreationDate": "D:20130729015932"
 		},
@@ -34,10 +34,10 @@
 					"dir": "ltr",
 					"width": 140,
 					"height": 20,
-					"fontName": "ºÚÌå"
+					"fontName": "g_d0_f1"
 				}
 			]
 		}
 	],
 	"filename": "./example-cmap.pdf"
-}
+}