Merge branch 'master' into bump-deps

.babelrc

@@ -5,7 +5,7 @@
       {
         "modules": false,
         "targets": {
-          "node": "6.10"
+          "node": "18"
         }
       }
     ]
@@ -17,11 +17,11 @@
           "@babel/preset-env",
           {
             "targets": {
-              "node": "6.10"
+              "node": "18"
             }
           }
         ]
       ]
     }
   }
-}
+}

.github/workflows/lint-test.yml

@@ -7,23 +7,22 @@ on: [push, pull_request]
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
 
     strategy:
       fail-fast: false
       matrix:
-        node-version: [14.x, 16.x]
+        node-version: [18.x, 20.x]
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Use Node.js ${{ matrix.node-version }}
-      uses: actions/setup-node@v1
-      with:
-        node-version: ${{ matrix.node-version }}
-    - name: Install dependencies
-      run: yarn --frozen-lockfile
-    - name: Run ESLint
-      run: npm run lint
-    - name: Run tests
-      run: npm test
+      - uses: actions/checkout@v2
+      - name: Use Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v1
+        with:
+          node-version: ${{ matrix.node-version }}
+      - name: Install dependencies
+        run: yarn --frozen-lockfile
+      - name: Run ESLint
+        run: npm run lint
+      - name: Run tests
+        run: npm test

CHANGELOG.md

@@ -1,6 +1,27 @@
 ## pdfkit changelog
 
-### Unreleased
+### [v0.15.1] - 2024-10-30
+
+- Fix browserify transform sRGB_IEC61966_2_1.icc file
+- Fix time comparison check equality embedded files
+
+### [v0.15.0] - 2024-03-23
+
+- Add subset for PDF/UA
+- Fix for line breaks in list items (#1486)
+- Fix for soft hyphen not being replaced by visible hyphen if necessary (#457)
+- Optimize output files by ignoring identity transforms
+- Fix for Acroforms - setting an option to false will still apply the flag (#1495)
+- Fix for text extraction in PDFium-based viewers due to invalid ToUnicodeMap (#1498)
+- Remove deprecated `write` method
+- Drop support for Node.js < 18 and for browsers released before 2020
+
+### [v0.14.0] - 2023-11-09
+
+- Add support for PDF/A-1b, PDF/A-1a, PDF/A-2b, PDF/A-2a, PDF/A-3b, PDF/A-3a
+- Update crypto-js to v4.2.0 (properly fix security issue)
+
+- Add support for EXIF orientation on JPEG images (#626 and #1353)
 
 ### [v0.13.0] - 2021-10-24
 

README.md

@@ -31,7 +31,7 @@ Installation uses the [npm](http://npmjs.org/) package manager. Just type the fo
   - Transformations
   - Linear and radial gradients
 - Text
-  - Line wrapping
+  - Line wrapping (with soft hyphen recognition)
   - Text alignments
   - Bulleted lists
 - Font embedding
@@ -129,7 +129,7 @@ complex documents with a very small amount of code. For more, see the `demo` fol
 There are three ways to use PDFKit in the browser:
 
 - Use [Browserify](http://browserify.org/). See demo [source code](demo/browser.js) and [build script](https://github.com/foliojs/pdfkit/blob/master/package.json#L56)
-- Use [webpack](https://webpack.js.org/). See [complete example](https://github.com/blikblum/pdfkit-webpack-example).
+- Use [webpack](https://webpack.js.org/). See [complete example](examples/webpack).
 - Use prebuilt version. Distributed as `pdfkit.standalone.js` file in the [releases](https://github.com/foliojs/pdfkit/releases) or in the package `js` folder.
 
 In addition to PDFKit, you'll need somewhere to stream the output to. HTML5 has a

docs/accessibility.md

@@ -14,6 +14,8 @@ Universal Accessibility) document (which is an extension of Tagged PDF):
  * Pass the option `pdfVersion: '1.5'` (or a higher version) when creating your `PDFDocument`
    (depending on the features you use, you may only need 1.4; refer to the PDF reference for
    details).
+ * Pass the option `subset: 'PDF/UA'` when creating your `PDFDocument` (if you wish the PDF to
+   be identified as PDF/UA-1).
  * Pass the option `tagged: true` when creating your `PDFDocument` (technically, this sets the
    `Marked` property in the `Markings` dictionary to `true` in the PDF).
  * Provide a `Title` in the `info` option, and pass `displayTitle: true` when creating your

docs/getting_started.md

@@ -14,7 +14,7 @@ in your JavaScript source file and create an instance of the
 `PDFDocument` class.
 
     const PDFDocument = require('pdfkit');
-    const doc = new PDFDocument;
+    const doc = new PDFDocument();
 
 `PDFDocument` instances are readable Node streams. They don't get saved anywhere automatically,
 but you can call the `pipe` method to send the output of the PDF document to another
@@ -259,6 +259,36 @@ Available options includes:
 When using PDF version 1.7 ExtensionLevel 3, password is truncated to 127 bytes of its UTF-8 representation.
 In older versions, password is truncated to 32 bytes, and only Latin-1 characters are allowed.
 
+## PDF/A
+
+PDF/A is a standard (ISO 19005-1:2005) which defines rules for electornic documents intended for long-term archiving.
+The restrictions on PDF/A documents are:
+
+- Cannot be encrypted
+- Fonts must be embedded
+- No JavaScript
+- No audio content
+- No video content
+- Addition of XMP metadata
+- Must define color spaces
+
+Currently, PDFKit aims to support PDF/A-1b, PDF/A-2b, PDF/A-3b and PDF/A-1a, PDF/A-2a, PDF/A-3a standards, also known as level B conformance and level A conformance, respectively.
+
+In order to create PDF/A documents, set `subset` to either `PDF/A-1` or `PDF/A-1b` for level B (basic) conformance, or `PDF/A-1a` for level A (accessible) conformance when creating the `PDFDocument` in `options` object.
+
+Similary, use `PDF/A-2` or `PDF/A-2b` for PDF/A-2 level B conformance and `PDF/A-2a` for PDF/A-2 level A conformance. `PDF/A-3` or `PDF/A-3b` can be used for PDF/A-3 level B conformance and `PDF/A-3a` for PDF/A-3 level A conformance.
+
+Futhermore, you will need to specify the other options relevant to the PDF/A subset you wish to use, for PDF/A-1 being:
+
+- `pdfVersion` set to at least `1.4`
+- `tagged` set to `true` for PDF/A-1a
+
+For PDF/A-2 and PDF/A-3, the `pdfVersion` needs to be set to at least `1.7` and `tagged` needs to be `true` for level A conformance.
+
+In order to verify the generated document for PDF/A and its subsets conformance, veraPDF is an excellent open source validator.
+
+Please note that PDF/A requires fonts to be embedded, as such the standard fonts PDFKit comes with cannot be used because they are in AFM format, which only provides neccessary metrics, without the font data. You should use `registerFont()` and use embeddable fonts such as `ttf`.
+
 ### Adding content
 
 Once you've created a `PDFDocument` instance, you can add content to the

docs/images.md

@@ -7,21 +7,22 @@ rendered at the current point in the text flow (below the last line of text).
 Otherwise, it is positioned absolutely at the specified point. The image will
 be scaled according to the following options.
 
-* Neither `width` or `height` provided - image is rendered at full size
-* `width` provided but not `height` - image is scaled proportionally to fit in the provided `width`
-* `height` provided but not `width` - image is scaled proportionally to fit in the provided `height`
-* Both `width` and `height` provided - image is stretched to the dimensions provided
-* `scale` factor provided - image is scaled proportionally by the provided scale factor
-* `fit` array provided - image is scaled proportionally to fit within the passed width and height
-* `cover` array provided - image is scaled proportionally to completely cover the rectangle defined by the passed width and height
-* `link` - a URL to link this image to (shortcut to create an annotation)
-* `goTo` - go to anchor (shortcut to create an annotation)
-* `destination` - create anchor to this image
+- Neither `width` or `height` provided - image is rendered at full size
+- `width` provided but not `height` - image is scaled proportionally to fit in the provided `width`
+- `height` provided but not `width` - image is scaled proportionally to fit in the provided `height`
+- Both `width` and `height` provided - image is stretched to the dimensions provided
+- `scale` factor provided - image is scaled proportionally by the provided scale factor
+- `fit` array provided - image is scaled proportionally to fit within the passed width and height
+- `cover` array provided - image is scaled proportionally to completely cover the rectangle defined by the passed width and height
+- `link` - a URL to link this image to (shortcut to create an annotation)
+- `goTo` - go to anchor (shortcut to create an annotation)
+- `destination` - create anchor to this image
+- `ignoreOrientation` - (true/false) ignore JPEG EXIF orientation. By default, images with JPEG EXIF orientation are properly rotated and/or flipped. Defaults to `false`, unless `ignoreOrientation` option set to `true` when creating the `PDFDocument` object (e.g. `new PDFDocument({ignoreOrientation: true})`)
 
 When a `fit` or `cover` array is provided, PDFKit accepts these additional options:
 
-* `align` - horizontally align the image, the possible values are `'left'`, `'center'` and `'right'`
-* `valign` - vertically align the image, the possible values are `'top'`, `'center'` and `'bottom'`
+- `align` - horizontally align the image, the possible values are `'left'`, `'center'` and `'right'`
+- `valign` - vertically align the image, the possible values are `'top'`, `'center'` and `'bottom'`
 
 Here is an example showing some of these options.
 
@@ -48,11 +49,11 @@ Here is an example showing some of these options.
        .rect(430, 15, 100, 100).stroke()
        .text('Centered', 430, 0);
 
-* * *
+---
 
 This example produces the following output:
 
-![0](images/images.png "400")
+![0](images/images.png '400')
 
 That is all there is to adding images to your PDF documents with PDFKit. Now
 let's look at adding outlines.

examples/kitchen-sink.js

@@ -1,4 +1,4 @@
-var PDFDocument = require('../js/pdfkit');
+var PDFDocument = require('../');
 var tiger = require('./tiger');
 var fs = require('fs');
 

examples/webpack/package.json

@@ -1,20 +1,20 @@
 {
   "license": "MIT",
   "dependencies": {
-    "assert": "^2.0.0",
+    "assert": "^2.1.0",
     "brace": "^0.11.1",
     "browserify-zlib": "^0.2.0",
     "buffer": "^6.0.3",
-    "pdfkit": "^0.12.3",
+    "pdfkit": "^0.15.0",
     "process": "^0.11.10",
-    "readable-stream": "^3.6.0",
-    "util": "^0.12.4"
+    "readable-stream": "^4.5.2",
+    "util": "^0.12.5"
   },
   "devDependencies": {
-    "html-webpack-plugin": "^5.3.2",
+    "html-webpack-plugin": "^5.6.0",
     "transform-loader": "^0.2.4",
-    "webpack": "^5.44.0",
-    "webpack-cli": "^4.7.2"
+    "webpack": "^5.91.0",
+    "webpack-cli": "^5.1.4"
   },
   "scripts": {
     "dev": "webpack --mode development",

lib/document.js

@@ -4,7 +4,6 @@ By Devon Govett
 */
 
 import stream from 'stream';
-import fs from 'fs';
 import PDFObject from './object';
 import PDFReference from './reference';
 import PDFPage from './page';
@@ -21,6 +20,8 @@ import MarkingsMixin from './mixins/markings';
 import AcroFormMixin from './mixins/acroform';
 import AttachmentsMixin from './mixins/attachments';
 import LineWrapper from './line_wrapper';
+import SubsetMixin from './mixins/subsets';
+import MetadataMixin from './mixins/metadata';
 
 class PDFDocument extends stream.Readable {
   constructor(options = {}) {
@@ -83,13 +84,15 @@ class PDFDocument extends stream.Readable {
     this.page = null;
 
     // Initialize mixins
+    this.initMetadata();
     this.initColor();
     this.initVector();
     this.initFonts(options.font);
     this.initText();
     this.initImages();
     this.initOutline();
     this.initMarkings(options);
+    this.initSubset(options);
 
     // Initialize the metadata
     this.info = {
@@ -216,7 +219,9 @@ class PDFDocument extends stream.Readable {
   addNamedEmbeddedFile(name, ref) {
     if (!this._root.data.Names.data.EmbeddedFiles) {
       // disabling /Limits for this tree fixes attachments not showing in Adobe Reader
-      this._root.data.Names.data.EmbeddedFiles = new PDFNameTree({ limits: false });
+      this._root.data.Names.data.EmbeddedFiles = new PDFNameTree({
+        limits: false
+      });
     }
 
     // add filespec to EmbeddedFiles
@@ -266,22 +271,9 @@ class PDFDocument extends stream.Readable {
     }
   }
 
-  write(filename, fn) {
-    // print a deprecation warning with a stacktrace
-    const err = new Error(`\
-PDFDocument#write is deprecated, and will be removed in a future version of PDFKit. \
-Please pipe the document into a Node stream.\
-`);
-
-    console.warn(err.stack);
-
-    this.pipe(fs.createWriteStream(filename));
-    this.end();
-    return this.once('end', fn);
-  }
-
   end() {
     this.flushPages();
+
     this._info = this.ref();
     for (let key in this.info) {
       let val = this.info[key];
@@ -305,6 +297,12 @@ Please pipe the document into a Node stream.\
     this.endOutline();
     this.endMarkings();
 
+    if (this.subset) {
+      this.endSubset();
+    }
+
+    this.endMetadata();
+
     this._root.end();
     this._root.data.Pages.end();
     this._root.data.Names.end();
@@ -368,6 +366,7 @@ const mixin = methods => {
   Object.assign(PDFDocument.prototype, methods);
 };
 
+mixin(MetadataMixin);
 mixin(ColorMixin);
 mixin(VectorMixin);
 mixin(FontsMixin);
@@ -378,6 +377,7 @@ mixin(OutlineMixin);
 mixin(MarkingsMixin);
 mixin(AcroFormMixin);
 mixin(AttachmentsMixin);
+mixin(SubsetMixin);
 
 PDFDocument.LineWrapper = LineWrapper;
 

lib/font/embedded.js

@@ -180,6 +180,15 @@ class EmbeddedFont extends PDFFont {
       descriptor.data.FontFile2 = fontFile;
     }
 
+    if (this.document.subset) {
+      const CIDSet = Buffer.from('FFFFFFFFC0', 'hex');
+      const CIDSetRef = this.document.ref();
+      CIDSetRef.write(CIDSet);
+      CIDSetRef.end();
+
+      descriptor.data.CIDSet = CIDSetRef;
+    }
+
     descriptor.end();
 
     const descendantFontData = {
@@ -240,6 +249,15 @@ class EmbeddedFont extends PDFFont {
       entries.push(`<${encoded.join(' ')}>`);
     }
 
+    const chunkSize = 256;
+    const chunks = Math.ceil(entries.length / chunkSize);
+    const ranges = [];
+    for (let i = 0; i < chunks; i++) {
+      const start = i * chunkSize;
+      const end = Math.min((i + 1) * chunkSize, entries.length);
+      ranges.push(`<${toHex(start)}> <${toHex(end - 1)}> [${entries.slice(start, end).join(' ')}]`);
+    }
+
     cmap.end(`\
 /CIDInit /ProcSet findresource begin
 12 dict begin
@@ -255,7 +273,7 @@ begincmap
 <0000><ffff>
 endcodespacerange
 1 beginbfrange
-<0000> <${toHex(entries.length - 1)}> [${entries.join(' ')}]
+${ranges.join('\n')}
 endbfrange
 endcmap
 CMapName currentdict /CMap defineresource pop

lib/image.js

@@ -16,7 +16,7 @@ class PDFImage {
       data = Buffer.from(new Uint8Array(src));
     } else {
       let match;
-      if ((match = /^data:.+;base64,(.*)$/.exec(src))) {
+      if ((match = /^data:.+?;base64,(.*)$/.exec(src))) {
         data = Buffer.from(match[1], 'base64');
       } else {
         data = fs.readFileSync(src);