UnicodeWrite

1//
2// Copyright (c) 2001-2020 by PDFTron Systems Inc. All Rights Reserved.
3//
4
5using System;
6using System.IO;
7using System.Threading.Tasks;
8using Windows.Foundation;
9
10using pdftron.Filters;
11using pdftron.PDF;
12using pdftron.SDF;
13
14using PDFNetUniversalSamples.ViewModels;
15using Windows.UI.Xaml.Media;
16using Windows.UI.Core;
17using System.Text;
18
19namespace PDFNetSamples
20{
21    // This example illustrates how to create Unicode text and how to embed composite fonts.
22    // 
23    // Note: This demo attempts to make use of 'arialuni.ttf' in the '/Samples/TestFiles' 
24    // directory. Arial Unicode MS is about 24MB in size and used to come together with Windows and 
25    // MS Office.
26    // 
27    // In case you don't have access to Arial Unicode MS you can use another wide coverage
28    // font, like Google Noto, GNU UniFont, or cyberbit. Many of these are freely available,
29    // and there is a list maintained at https://en.wikipedia.org/wiki/Unicode_font
30    // 
31    // If no specific font file can be loaded, the demo will fall back to system specific font
32    // substitution routines, and the result will depend on which fonts are available.
33    class UnicodeWriteTest : Sample
34    {
35        public UnicodeWriteTest() : 
36            base ("UnicodeWrite", "This example illustrates how to create Unicode text and how to embed composite fonts.")
37        {
38        }
39
40        public override IAsyncAction RunAsync()
41        {
42            pdftron.PDFNet.Initialize();
43
44            
45
46            return Task.Run(new System.Action(async () => 
47            {
48                try
49                {
50                    PDFDoc doc = new PDFDoc();
51
52                    ElementBuilder eb = new ElementBuilder();	// ElementBuilder is used to build new Element objects
53                    ElementWriter writer = new ElementWriter();	// ElementWriter is used to write Elements to the page	
54
55                    Page page = doc.PageCreate(new pdftron.PDF.Rect(0, 0, 612, 794)); // Start a new page
56
57                    writer.Begin(page);	// begin writing to this page
58
59                    Font fnt = null;
60                    try
61                    {
62                        fnt = Font.Create(doc, "Arial", "");
63                    }
64                    catch (Exception e)
65                    {
66                        WriteLine("Exception:" + e.Message);
67                    }
68
69                    if (fnt == null)
70                    {
71                        try
72                        {
73                            fnt = Font.CreateCIDTrueTypeFont(doc, "ARIALUNI.TTF", true, true);
74                        }
75                        catch (Exception e)
76                        {
77                            WriteLine("Exception:" + e.Message);
78                        }
79                    } else if (fnt == null)
80                    {
81                        try
82                        {
83                            fnt = Font.CreateCIDTrueTypeFont(doc, "C:/Windows/Fonts/ARIALUNI.TTF", true, true);
84                        }
85                        catch (Exception e)
86                        {
87                            WriteLine("Exception:" + e.Message);
88                        }
89                    } else if (fnt == null)
90                    {
91                        WriteLine("Note: using system font substitution for unshaped unicode text");
92                        fnt = Font.Create(doc, "Helvetica", "");
93                    }
94                    else
95                    {
96                        WriteLine("Note: using Arial Unicode for unshaped unicode text");
97                    }
98
99                    Element element = eb.CreateTextBegin(fnt, 1);
100                    element.SetTextMatrix(10, 0, 0, 10, 50, 600);
101                    element.GetGState().SetLeading(2); // Set the spacing between lines
102                    writer.WriteElement(element);
103
104                    // Hello World!!!
105                    string hello = "Hello World!";
106                    writer.WriteElement(eb.CreateUnicodeTextRun(hello));
107                    writer.WriteElement(eb.CreateTextNewLine());
108
109                    // Latin
110                    char[] latin = {
111                                'a', 'A', 'b', 'B', 'c', 'C', 'd', 'D', '\x45', '\x0046', '\x00C0',
112                                '\x00C1', '\x00C2', '\x0143', '\x0144', '\x0145', '\x0152', '1', '2' // etc.
113					};
114                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(latin)));
115                    writer.WriteElement(eb.CreateTextNewLine());
116
117                    // Greek
118                    char[] greek = {
119                                (char)0x039E, (char)0x039F, (char)0x03A0, (char)0x03A1, (char)0x03A3,
120                                (char)0x03A6, (char)0x03A8, (char)0x03A9  // etc.
121							};
122                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(greek)));
123                    writer.WriteElement(eb.CreateTextNewLine());
124
125                    // Cyrillic
126                    char[] cyrillic = {
127                                (char)0x0409, (char)0x040A, (char)0x040B, (char)0x040C, (char)0x040E, (char)0x040F, (char)0x0410, (char)0x0411,
128                                (char)0x0412, (char)0x0413, (char)0x0414, (char)0x0415, (char)0x0416, (char)0x0417, (char)0x0418, (char)0x0419 // etc.
129							};
130                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(cyrillic)));
131                    writer.WriteElement(eb.CreateTextNewLine());
132
133                    // Hebrew
134                    char[] hebrew = {
135                                (char)0x05D0, (char)0x05D1, (char)0x05D3, (char)0x05D3, (char)0x05D4, (char)0x05D5, (char)0x05D6, (char)0x05D7, (char)0x05D8,
136                                (char)0x05D9, (char)0x05DA, (char)0x05DB, (char)0x05DC, (char)0x05DD, (char)0x05DE, (char)0x05DF, (char)0x05E0, (char)0x05E1 // etc. 
137							};
138                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(hebrew)));
139                    writer.WriteElement(eb.CreateTextNewLine());
140
141                    // Arabic
142                    char[] arabic = {
143                                (char)0x0624, (char)0x0625, (char)0x0626, (char)0x0627, (char)0x0628, (char)0x0629, (char)0x062A, (char)0x062B, (char)0x062C,
144                                (char)0x062D, (char)0x062E, (char)0x062F, (char)0x0630, (char)0x0631, (char)0x0632, (char)0x0633, (char)0x0634, (char)0x0635 // etc. 
145							};
146                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(arabic)));
147                    writer.WriteElement(eb.CreateTextNewLine());
148
149                    // Thai 
150                    char[] thai = {
151                                (char)0x0E01, (char)0x0E02, (char)0x0E03, (char)0x0E04, (char)0x0E05, (char)0x0E06, (char)0x0E07, (char)0x0E08, (char)0x0E09,
152                                (char)0x0E0A, (char)0x0E0B, (char)0x0E0C, (char)0x0E0D, (char)0x0E0E, (char)0x0E0F, (char)0x0E10, (char)0x0E11, (char)0x0E12 // etc. 
153							};
154                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(thai)));
155                    writer.WriteElement(eb.CreateTextNewLine());
156
157                    // Hiragana - Japanese 
158                    char[] hiragana = {
159                                (char)0x3041, (char)0x3042, (char)0x3043, (char)0x3044, (char)0x3045, (char)0x3046, (char)0x3047, (char)0x3048, (char)0x3049,
160                                (char)0x304A, (char)0x304B, (char)0x304C, (char)0x304D, (char)0x304E, (char)0x304F, (char)0x3051, (char)0x3051, (char)0x3052 // etc. 
161							};
162                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(hiragana)));
163                    writer.WriteElement(eb.CreateTextNewLine());
164
165                    // CJK Unified Ideographs
166                    char[] cjk_uni = {
167                                (char)0x5841, (char)0x5842, (char)0x5843, (char)0x5844, (char)0x5845, (char)0x5846, (char)0x5847, (char)0x5848, (char)0x5849,
168                                (char)0x584A, (char)0x584B, (char)0x584C, (char)0x584D, (char)0x584E, (char)0x584F, (char)0x5850, (char)0x5851, (char)0x5852 // etc. 
169							};
170                    writer.WriteElement(eb.CreateUnicodeTextRun(new string(cjk_uni)));
171                    writer.WriteElement(eb.CreateTextNewLine());
172
173                    // Finish the block of text
174                    writer.WriteElement(eb.CreateTextEnd());
175
176                    WriteLine("Now using text shaping logic to place text");
177
178                    // Create a font in indexed encoding mode 
179                    // normally this would mean that we are required to provide glyph indices
180                    // directly to CreateUnicodeTextRun, but instead, we will use the GetShapedText
181                    // method to take care of this detail for us.
182                    Font indexedFont = Font.CreateCIDTrueTypeFont(doc, Path.Combine(InputPath, "NotoSans_with_hindi.ttf"), true, true, FontEncoding.e_Indices);
183                    element = eb.CreateTextBegin(indexedFont, 10.0);
184                    writer.WriteElement(element);
185
186                    double linePos = 350.0;
187                    double lineSpace = 20.0;
188
189                    // Transform unicode text into an abstract collection of glyph indices and positioning info 
190                    ShapedText shapedText = indexedFont.GetShapedText("Shaped Hindi Text:");
191
192                    // transform the shaped text info into a PDF element and write it to the page
193                    element = eb.CreateShapedTextRun(shapedText);
194                    element.SetTextMatrix(1.5, 0, 0, 1.5, 50, linePos);
195                    linePos -= lineSpace;
196                    writer.WriteElement(element);
197
198                    // read in unicode text lines from a file 
199
200                    string[] hindiTextLines = File.ReadAllLines(Path.Combine(InputPath, "hindi_sample_utf16le.txt"), new UnicodeEncoding());
201
202                    WriteLine("Read in " + hindiTextLines.Length + " lines of Unicode text from file");
203                    foreach (string textLine in hindiTextLines)
204                    {
205                        shapedText = indexedFont.GetShapedText(textLine);
206                        element = eb.CreateShapedTextRun(shapedText);
207                        element.SetTextMatrix(1.5, 0, 0, 1.5, 50, linePos);
208                        linePos -= lineSpace;
209                        writer.WriteElement(element);
210                        WriteLine("Wrote shaped line to page");
211                    }
212
213                    // Finish the shaped block of text
214                    writer.WriteElement(eb.CreateTextEnd());
215
216                    writer.End();  // save changes to the current page
217                    doc.PagePushBack(page);
218
219                    await doc.SaveAsync(Path.Combine(OutputPath, "unicodewrite.pdf"), 
220                        SDFDocSaveOptions.e_linearized | SDFDocSaveOptions.e_hex_strings);
221
222                    await AddFileToOutputList(Path.Combine(OutputPath, "unicodewrite.pdf"));
223
224                    WriteLine("Done. Result saved in unicodewrite.pdf...");
225                }
226                catch (Exception e)
227                {
228                    WriteLine(GetExceptionMessage(e));
229                }
230
231            })).AsAsyncAction();
232        }
233    }
234}