Section:

Create Unicode Text, Embed CID in PDFs - Java Sample Code

Sample code for using Apryse SDK to create Unicode text and embed composite fonts in PDF files. Samples provided in Python, C++, C#, Java, Node.js (JavaScript), PHP, Ruby, Go and VB. Learn more about our Server SDK.

1//---------------------------------------------------------------------------------------
2// Copyright (c) 2001-2024 by Apryse Software Inc. All Rights Reserved.
3// Consult legal.txt regarding legal and license information.
4//---------------------------------------------------------------------------------------
5
6import com.pdftron.pdf.*;
7import com.pdftron.sdf.SDFDoc;
8import java.util.List;
9import java.nio.file.Files;
10import java.nio.file.Paths;
11import java.nio.charset.StandardCharsets;
12
13/**
14 * This example illustrates how to create Unicode text and how to embed composite fonts.
15 * <p>
16 * Note: This demo attempts to make use of 'arialuni.ttf' in the '/Samples/TestFiles' 
17 * directory. Arial Unicode MS is about 24MB in size and used to come together with Windows and 
18 * MS Office.
19 * <p>
20 * In case you don't have access to Arial Unicode MS you can use another wide coverage
21 * font, like Google Noto, GNU UniFont, or cyberbit. Many of these are freely available,
22 * and there is a list maintained at https://en.wikipedia.org/wiki/Unicode_font
23 * <p>
24 * If no specific font file can be loaded, the demo will fall back to system specific font
25 * substitution routines, and the result will depend on which fonts are available.
26 * 
27 */
28public class UnicodeWriteTest {
29    public static void main(String[] args) {
30        PDFNet.initialize(PDFTronLicense.Key());
31
32        // Relative path to the folder containing test files.
33        String input_path = "../../TestFiles/";
34        String output_path = "../../TestFiles/Output/";
35
36        try (PDFDoc doc = new PDFDoc()) {
37            ElementBuilder eb = new ElementBuilder();
38            ElementWriter writer = new ElementWriter();
39
40            // Start a new page ------------------------------------
41            Page page = doc.pageCreate(new Rect(0, 0, 612, 794));
42
43            writer.begin(page);    // begin writing to this page
44
45            String fontLocation = input_path + "ARIALUNI.TTF";
46
47            Font fnt = null;
48            try {
49                // Embed and subset the font
50                fnt = Font.createCIDTrueTypeFont(doc, fontLocation, true, true);
51            } catch (Exception e) {
52                fontLocation = "C:/Windows/Fonts/ARIALUNI.TTF";
53                try {
54                     fnt = Font.createCIDTrueTypeFont(doc, fontLocation, true, true);
55                }
56                catch (Exception e2) {
57                    fontLocation = null;
58                }
59            }
60
61            if(fnt != null) {
62                System.out.println("Note: using " + fontLocation + " for unshaped unicode text");
63            }
64            else {
65                System.out.println("Note: using system font substitution for unshaped unicode text");
66                fnt = Font.create(doc, "Helvetica", "");
67            }
68
69            Element element = eb.createTextBegin(fnt, 1);
70            element.setTextMatrix(10, 0, 0, 10, 50, 600);
71            element.getGState().setLeading(2);         // Set the spacing between lines
72            writer.writeElement(element);
73
74            // Hello World!
75            char hello[] = {'H', 'e', 'l', 'l', 'o', ' ', 'W', 'o', 'r', 'l', 'd', '!'};
76            writer.writeElement(eb.createUnicodeTextRun(new String(hello)));
77            writer.writeElement(eb.createTextNewLine());
78
79            // Latin
80            char latin[] = {
81                    'a', 'A', 'b', 'B', 'c', 'C', 'd', 'D', 0x45, 0x0046, 0x00C0,
82                    0x00C1, 0x00C2, 0x0143, 0x0144, 0x0145, 0x0152, '1', '2' // etc.
83            };
84            writer.writeElement(eb.createUnicodeTextRun(new String(latin)));
85            writer.writeElement(eb.createTextNewLine());
86
87            // Greek
88            char greek[] = {
89                    0x039E, 0x039F, 0x03A0, 0x03A1, 0x03A3, 0x03A6, 0x03A8, 0x03A9  // etc.
90            };
91            writer.writeElement(eb.createUnicodeTextRun(new String(greek)));
92            writer.writeElement(eb.createTextNewLine());
93
94            // Cyrillic
95            char cyrilic[] = {
96                    0x0409, 0x040A, 0x040B, 0x040C, 0x040E, 0x040F, 0x0410, 0x0411,
97                    0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419 // etc.
98            };
99            writer.writeElement(eb.createUnicodeTextRun(new String(cyrilic)));
100            writer.writeElement(eb.createTextNewLine());
101
102            // Hebrew
103            char hebrew[] = {
104                    0x05D0, 0x05D1, 0x05D3, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8,
105                    0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF, 0x05E0, 0x05E1 // etc.
106            };
107            writer.writeElement(eb.createUnicodeTextRun(new String(hebrew)));
108            writer.writeElement(eb.createTextNewLine());
109
110            // Arabic
111            char arabic[] = {
112                    0x0624, 0x0625, 0x0626, 0x0627, 0x0628, 0x0629, 0x062A, 0x062B, 0x062C,
113                    0x062D, 0x062E, 0x062F, 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635 // etc.
114            };
115            writer.writeElement(eb.createUnicodeTextRun(new String(arabic)));
116            writer.writeElement(eb.createTextNewLine());
117
118            // Thai
119            char thai[] = {
120                    0x0E01, 0x0E02, 0x0E03, 0x0E04, 0x0E05, 0x0E06, 0x0E07, 0x0E08, 0x0E09,
121                    0x0E0A, 0x0E0B, 0x0E0C, 0x0E0D, 0x0E0E, 0x0E0F, 0x0E10, 0x0E11, 0x0E12 // etc.
122            };
123            writer.writeElement(eb.createUnicodeTextRun(new String(thai)));
124            writer.writeElement(eb.createTextNewLine());
125
126            // Hiragana - Japanese
127            char hiragana[] = {
128                    0x3041, 0x3042, 0x3043, 0x3044, 0x3045, 0x3046, 0x3047, 0x3048, 0x3049,
129                    0x304A, 0x304B, 0x304C, 0x304D, 0x304E, 0x304F, 0x3051, 0x3051, 0x3052 // etc.
130            };
131            writer.writeElement(eb.createUnicodeTextRun(new String(hiragana)));
132            writer.writeElement(eb.createTextNewLine());
133
134            // CJK Unified Ideographs
135            char cjk_uni[] = {
136                    0x5841, 0x5842, 0x5843, 0x5844, 0x5845, 0x5846, 0x5847, 0x5848, 0x5849,
137                    0x584A, 0x584B, 0x584C, 0x584D, 0x584E, 0x584F, 0x5850, 0x5851, 0x5852 // etc.
138            };
139            writer.writeElement(eb.createUnicodeTextRun(new String(cjk_uni)));
140            writer.writeElement(eb.createTextNewLine());
141
142            // Simplified Chinese
143            char chinese_simplified[] = {
144              0x4e16, 0x754c, 0x60a8, 0x597d
145            };
146            writer.writeElement(eb.createUnicodeTextRun(new String(chinese_simplified)));
147            writer.writeElement(eb.createTextNewLine());
148
149            // Finish the block of text
150            writer.writeElement(eb.createTextEnd());
151
152            System.out.println("Now using text shaping logic to place text");
153
154            // Create a font in indexed encoding mode 
155            // normally this would mean that we are required to provide glyph indices
156            // directly to CreateUnicodeTextRun, but instead, we will use the GetShapedText
157            // method to take care of this detail for us.
158            Font indexedFont = Font.createCIDTrueTypeFont(doc, input_path + "NotoSans_with_hindi.ttf", true, true, Font.e_Indices);
159            element = eb.createTextBegin(indexedFont, 10.0);
160            writer.writeElement(element);
161
162            double linePos = 350.0;
163            double lineSpace = 20.0;
164
165            // Transform unicode text into an abstract collection of glyph indices and positioning info 
166            ShapedText shapedText = indexedFont.getShapedText("Shaped Hindi Text:");
167
168            // transform the shaped text info into a PDF element and write it to the page
169            element = eb.createShapedTextRun(shapedText);
170            element.setTextMatrix(1.5, 0, 0, 1.5, 50, linePos);
171            linePos -= lineSpace;
172            writer.writeElement(element);
173
174            // read in unicode text lines from a file 
175            List<String> hindiTextLines = Files.readAllLines(Paths.get(input_path + "hindi_sample_utf16le.txt"), StandardCharsets.UTF_16LE);
176
177            System.out.println("Read in " + hindiTextLines.size() + " lines of Unicode text from file");
178            for (String textLine : hindiTextLines)  
179            {
180                shapedText = indexedFont.getShapedText(textLine);
181                element = eb.createShapedTextRun(shapedText);
182                element.setTextMatrix(1.5, 0, 0, 1.5, 50, linePos);
183                linePos -= lineSpace;
184                writer.writeElement(element);
185                System.out.println("Wrote shaped line to page");
186            }
187        
188            // Finish the shaped block of text
189            writer.writeElement(eb.createTextEnd());
190
191
192            writer.end();  // save changes to the current page
193            doc.pagePushBack(page);
194
195            doc.save(output_path + "unicodewrite.pdf", new SDFDoc.SaveMode[]{SDFDoc.SaveMode.REMOVE_UNUSED, SDFDoc.SaveMode.HEX_STRINGS}, null);
196            System.out.println("Done. Result saved in unicodewrite.pdf...");
197        } catch (Exception e) {
198            e.printStackTrace();
199        }
200
201        PDFNet.terminate();
202    }
203
204}

Did you find this helpful?

Trial setup questions?

Ask experts on Discord

Need other help?

Contact Support

Pricing or product questions?

Contact Sales