Section:

Create Unicode Text, Embed CID in PDFs - Go 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) 2001-2021 by PDFTron Systems Inc. All Rights Reserved.
3// Consult LICENSE.txt regarding license information.
4//---------------------------------------------------------------------------------------
5
6package main
7import (
8	"fmt"
9    "os"
10    "bufio"
11    "strconv"
12    "runtime"
13	. "pdftron"
14    "golang.org/x/text/encoding/unicode"
15    "golang.org/x/text/transform"
16)
17
18import  "pdftron/Samples/LicenseKey/GO"
19
20// Relative path to the folder containing the test files.
21var inputPath = "../../TestFiles/"
22var outputPath = "../../TestFiles/Output/"
23
24// This example illustrates how to create Unicode text and how to embed composite fonts.
25// 
26// Note: This demo attempts to make use of 'arialuni.ttf' in the '/Samples/TestFiles' 
27// directory. Arial Unicode MS is about 24MB in size and used to come together with Windows and 
28// MS Office.
29// 
30// In case you don't have access to Arial Unicode MS you can use another wide coverage
31// font, like Google Noto, GNU UniFont, or cyberbit. Many of these are freely available,
32// and there is a list maintained at https://en.wikipedia.org/wiki/Unicode_font
33// 
34// If no specific font file can be loaded, the demo will fall back to system specific font
35// substitution routines, and the result will depend on which fonts are available.
36//
37// Run "go get golang.org/x/text/encoding/unicode" and "go get golang.org/x/text/transform" to install, 
38// if these two packages are not presented.
39 
40func ReadUnicodeTextLinesFromFile(  writer ElementWriter, 
41                                    indexedFont Font, 
42                                    eb ElementBuilder, 
43                                    linePos float64, 
44                                    lineSpace float64, 
45                                    showNumOfLines bool, 
46                                    readLines bool){
47    file, err := os.Open(inputPath + "hindi_sample_utf16le.txt")
48    if err != nil {
49        fmt.Println(err)
50    }
51    defer file.Close()
52    scanner := bufio.NewScanner(transform.NewReader(file, unicode.UTF16(unicode.LittleEndian, unicode.UseBOM).NewDecoder()))
53    i := 0
54    if(showNumOfLines){
55        for scanner.Scan() {
56            i++
57        }
58        fmt.Println("Read in " + strconv.Itoa(i) + " lines of Unicode text from file")
59    }else if(readLines){
60        for scanner.Scan() {
61            shapedText := indexedFont.GetShapedText(scanner.Text())
62            element := eb.CreateShapedTextRun(shapedText)
63            element.SetTextMatrix(1.5, 0.0, 0.0, 1.5, 50.0, linePos-lineSpace*(float64(i+1)))
64            writer.WriteElement(element)
65            fmt.Println("Wrote shaped line to page")  
66            i++
67        }
68    }
69    if err := scanner.Err(); err != nil {
70        fmt.Println(err)
71    }
72}
73
74func main(){
75    PDFNetInitialize(PDFTronLicense.Key)
76    
77    doc := NewPDFDoc()
78    eb := NewElementBuilder()
79    writer := NewElementWriter()
80    
81    // Start a new page ------------------------------------
82    page := doc.PageCreate(NewRect(0.0, 0.0, 612.0, 794.0))
83    
84    writer.Begin(page)    // begin writing to this page
85       
86    // Embed and subset the font
87    fontProgram := inputPath + "ARIALUNI.TTF"
88    fnt := FontCreate(doc.GetSDFDoc(), "Helvetica", "")
89    if _, err := os.Stat(fontProgram); err == nil{
90      // fontProgram exists
91      fnt = FontCreateCIDTrueTypeFont(doc.GetSDFDoc(), fontProgram, true, true)
92      fmt.Println("Note: using " + fontProgram + " for unshaped unicode text")
93    }else if os.IsNotExist(err){
94        if runtime.GOOS == "windows"{
95            fontProgram = "C:/Windows/Fonts/ARIALUNI.TTF"
96            if _, err := os.Stat(fontProgram); err == nil{
97              // fontProgram exists
98                fnt = FontCreateCIDTrueTypeFont(doc.GetSDFDoc(), fontProgram, true, true)
99                fmt.Println("Note: using " + fontProgram + " for unshaped unicode text")
100            }else if os.IsNotExist(err){
101                fmt.Println("Note: using system font substitution for unshaped unicode text")
102            }else{
103                fmt.Println(err)
104            }
105        }
106    }else{
107        fmt.Println(err)
108    }
109
110    element := eb.CreateTextBegin(fnt, 1.0)
111    element.SetTextMatrix(10.0, 0.0, 0.0, 10.0, 50.0, 600.0)
112    element.GetGState().SetLeading(2)         // Set the spacing between lines
113    writer.WriteElement(element)
114
115    // Hello World!
116    hello := []uint16{'H','e','l','l','o',' ','W','o','r','l','d','!'}
117    fmt.Println(hello)
118    writer.WriteElement(eb.CreateUnicodeTextRun(&hello[0], uint(len(hello))))
119    writer.WriteElement(eb.CreateTextNewLine())
120    
121    // Latin
122    latin := []uint16{'a', 'A', 'b', 'B', 'c', 'C', 'd', 'D', 0x45, 0x0046, 0x00C0, 
123            0x00C1, 0x00C2, 0x0143, 0x0144, 0x0145, 0x0152, '1', '2' }// etc.
124    writer.WriteElement(eb.CreateUnicodeTextRun(&latin[0], uint(len(latin))))
125    writer.WriteElement(eb.CreateTextNewLine())
126
127    // Greek
128    greek := []uint16{0x039E, 0x039F, 0x03A0, 0x03A1,0x03A3, 0x03A6, 0x03A8, 0x03A9}
129    writer.WriteElement(eb.CreateUnicodeTextRun(&greek[0], uint(len(greek))))
130    writer.WriteElement(eb.CreateTextNewLine())
131    
132    // Cyrillic
133    cyrillic := []uint16{0x0409, 0x040A, 0x040B, 0x040C, 0x040E, 0x040F, 0x0410, 0x0411,
134                0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419}
135    writer.WriteElement(eb.CreateUnicodeTextRun(&cyrillic[0], uint(len(cyrillic))))
136    writer.WriteElement(eb.CreateTextNewLine())
137    
138    // Hebrew
139    hebrew := []uint16{0x05D0, 0x05D1, 0x05D3, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8,
140              0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF, 0x05E0, 0x05E1}
141    writer.WriteElement(eb.CreateUnicodeTextRun(&hebrew[0], uint(len(hebrew))))
142    writer.WriteElement(eb.CreateTextNewLine())
143    
144    // Arabic
145    arabic := []uint16{0x0624, 0x0625, 0x0626, 0x0627, 0x0628, 0x0629, 0x062A, 0x062B, 0x062C,
146              0x062D, 0x062E, 0x062F, 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635}
147    writer.WriteElement(eb.CreateUnicodeTextRun(&arabic[0], uint(len(arabic))))
148    writer.WriteElement(eb.CreateTextNewLine())
149    
150    // Thai
151    thai := []uint16{0x0E01, 0x0E02, 0x0E03, 0x0E04, 0x0E05, 0x0E06, 0x0E07, 0x0E08, 0x0E09, 
152            0x0E0A, 0x0E0B, 0x0E0C, 0x0E0D, 0x0E0E, 0x0E0F, 0x0E10, 0x0E11, 0x0E12}
153    writer.WriteElement(eb.CreateUnicodeTextRun(&thai[0], uint(len(thai))))
154    writer.WriteElement(eb.CreateTextNewLine())
155    
156    // Hiragana - Japanese 
157    hiragana := []uint16{0x3041, 0x3042, 0x3043, 0x3044, 0x3045, 0x3046, 0x3047, 0x3048, 0x3049,
158                0x304A, 0x304B, 0x304C, 0x304D, 0x304E, 0x304F, 0x3051, 0x3051, 0x3052}
159    writer.WriteElement(eb.CreateUnicodeTextRun(&hiragana[0], uint(len(hiragana))))
160    writer.WriteElement(eb.CreateTextNewLine())
161    
162    // CJK Unified Ideographs 
163    cjk_uni := []uint16{0x5841, 0x5842, 0x5843, 0x5844, 0x5845, 0x5846, 0x5847, 0x5848, 0x5849, 
164               0x584A, 0x584B, 0x584C, 0x584D, 0x584E, 0x584F, 0x5850, 0x5851, 0x5852}
165    writer.WriteElement(eb.CreateUnicodeTextRun(&cjk_uni[0], uint(len(cjk_uni))))
166    writer.WriteElement(eb.CreateTextNewLine())
167    
168    // Simplified Chinese
169    chineseSimplified := []uint16{0x4e16, 0x754c, 0x60a8, 0x597d}
170    writer.WriteElement(eb.CreateUnicodeTextRun(&chineseSimplified[0], uint(len(chineseSimplified))))
171    writer.WriteElement(eb.CreateTextNewLine())
172
173    // Finish the block of text
174    writer.WriteElement(eb.CreateTextEnd())
175
176    fmt.Println("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    indexedFont := FontCreateCIDTrueTypeFont(doc.GetSDFDoc(), inputPath + "NotoSans_with_hindi.ttf", true, true, FontE_Indices)
183    element = eb.CreateTextBegin(indexedFont, 10.0)
184    writer.WriteElement(element)
185
186    linePos := 350.0
187    lineSpace := 20.0
188
189    // Transform unicode text into an abstract collection of glyph indices and positioning info 
190    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, 0.0, 1.5, 50.0, linePos)
195    writer.WriteElement(element)
196    // read in unicode text lines from a file
197    ReadUnicodeTextLinesFromFile(writer, indexedFont, eb, linePos, lineSpace, true, false)
198    ReadUnicodeTextLinesFromFile(writer, indexedFont, eb, linePos, lineSpace, false, true)
199    
200    // Finish the block of text
201    writer.WriteElement(eb.CreateTextEnd())
202
203    writer.End()    // save changes to the current page
204    doc.PagePushBack(page)
205    
206    doc.Save(outputPath + "unicodewrite.pdf", uint(SDFDocE_remove_unused | SDFDocE_hex_strings))
207    fmt.Println("Done. Result saved in unicodewrite.pdf...")
208    
209    doc.Close()
210    PDFNetTerminate()
211}

Did you find this helpful?

Trial setup questions?

Ask experts on Discord

Need other help?

Contact Support

Pricing or product questions?

Contact Sales