pdfkit: add Options.Subject and Keywords for the info dictionary

document.go

@@ -17,10 +17,15 @@ import (
 // Options configures a Document. The zero value is valid and yields a
 // deterministic, uncompressed document with no timestamps.
 type Options struct {
-	// Title and Author populate the document information dictionary. Empty
-	// values are omitted.
-	Title  string
-	Author string
+	// Title, Author, Subject and Keywords populate the document information
+	// dictionary. Empty values are omitted. Subject is a one-line description of
+	// the document; Keywords is a list of search terms (conventionally
+	// comma-separated). Each is written as a PDF text string, so a non-ASCII value
+	// is encoded UTF-16BE.
+	Title    string
+	Author   string
+	Subject  string
+	Keywords string
 
 	// Producer is the /Producer string in the information dictionary. When
 	// empty it defaults to DefaultProducer.
@@ -215,7 +220,8 @@ func (d *Document) Write(w io.Writer) error {
 	bd.put(catalog, catDict)
 
 	var info objRef
-	hasInfo := d.opts.Title != "" || d.opts.Author != "" || d.producer() != "" || d.opts.Now != nil
+	hasInfo := d.opts.Title != "" || d.opts.Author != "" || d.opts.Subject != "" ||
+		d.opts.Keywords != "" || d.producer() != "" || d.opts.Now != nil
 	if hasInfo {
 		info = bd.add(d.infoDict())
 	}
@@ -399,6 +405,12 @@ func (d *Document) infoDict() *pdfDict {
 	if d.opts.Author != "" {
 		info.set("Author", pdfTextString(d.opts.Author))
 	}
+	if d.opts.Subject != "" {
+		info.set("Subject", pdfTextString(d.opts.Subject))
+	}
+	if d.opts.Keywords != "" {
+		info.set("Keywords", pdfTextString(d.opts.Keywords))
+	}
 	if p := d.producer(); p != "" {
 		info.set("Producer", pdfString(p))
 	}

subjectkeywords_test.go

@@ -0,0 +1,40 @@
+// Copyright (c) the go-pdfkit/pdfkit authors.
+// SPDX-License-Identifier: BSD-3-Clause
+
+package pdfkit
+
+import (
+	"bytes"
+	"testing"
+)
+
+// Subject and Keywords reach the information dictionary as text strings.
+func TestInfoSubjectAndKeywords(t *testing.T) {
+	doc := New(Options{Subject: "A study of widgets", Keywords: "widgets, gadgets, gizmos"})
+	doc.AddPage(A4)
+	var b bytes.Buffer
+	if err := doc.Write(&b); err != nil {
+		t.Fatal(err)
+	}
+	for _, want := range []string{"/Subject (A study of widgets)", "/Keywords (widgets, gadgets, gizmos)"} {
+		if !bytes.Contains(b.Bytes(), []byte(want)) {
+			t.Errorf("output missing %q\n%s", want, b.String())
+		}
+	}
+}
+
+// A non-ASCII Subject/Keywords value is encoded UTF-16BE, like Title/Author.
+func TestInfoSubjectKeywordsAccentedUTF16(t *testing.T) {
+	doc := New(Options{Subject: "Résumé", Keywords: "clé, référence"})
+	doc.AddPage(A4)
+	var b bytes.Buffer
+	if err := doc.Write(&b); err != nil {
+		t.Fatal(err)
+	}
+	if !bytes.Contains(b.Bytes(), []byte("<FEFF")) {
+		t.Errorf("accented Subject/Keywords were not written UTF-16BE\n%s", b.String())
+	}
+	if bytes.Contains(b.Bytes(), []byte("Résumé")) {
+		t.Errorf("accented Subject leaked into the PDF as raw UTF-8")
+	}
+}