Created
April 12, 2021 10:19
-
-
Save tejash-jl/768adf9c2de684b5bdddbcfdbbb79ca7 to your computer and use it in GitHub Desktop.
PDFBox multi language support
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.example.evaluatems; | |
import org.apache.pdfbox.pdmodel.PDDocument; | |
import org.apache.pdfbox.pdmodel.PDPage; | |
import org.apache.pdfbox.pdmodel.PDPageContentStream; | |
import org.apache.pdfbox.pdmodel.font.PDFont; | |
import org.apache.pdfbox.pdmodel.font.PDType0Font; | |
import org.apache.pdfbox.pdmodel.font.PDType1Font; | |
import org.apache.pdfbox.pdmodel.font.encoding.GlyphList; | |
import org.apache.pdfbox.pdmodel.font.encoding.WinAnsiEncoding; | |
import java.io.File; | |
import java.io.IOException; | |
import java.nio.file.Files; | |
import java.nio.file.Path; | |
import java.nio.file.Paths; | |
import java.util.ArrayList; | |
import java.util.List; | |
import java.util.stream.Stream; | |
public class PDFGenerator { | |
public static void main(String[] args) throws IOException { | |
try (PDDocument doc = new PDDocument()) { | |
PDPage myPage = new PDPage(); | |
doc.addPage(myPage); | |
PDFont defaultFont = PDType1Font.TIMES_ROMAN; // default | |
List<PDFont> fonts = new ArrayList<>(); | |
fonts.add(defaultFont); | |
try (Stream<Path> paths = Files.walk(Paths.get("fonts"))) { | |
paths | |
.filter(path -> Files.isRegularFile(path) && path.toString().endsWith(".ttf")) | |
.forEach(x -> { | |
try { | |
fonts.add(PDType0Font.load(doc, new File(x.toString()))); | |
} catch (IOException e) { | |
e.printStackTrace(); | |
} | |
}); | |
} | |
try (PDPageContentStream cont = new PDPageContentStream(doc, myPage)) { | |
cont.beginText(); | |
cont.newLineAtOffset(20, 700); | |
showTextMultiple(cont, "abc ಬಾ s", fonts, 20); | |
cont.endText(); | |
} | |
doc.save("output.pdf"); | |
} | |
} | |
private static void showTextMultiple(PDPageContentStream cs, String text, List<PDFont> fonts, float size) | |
throws IOException { | |
try { | |
// first try all at once | |
fonts.get(0).encode(text); | |
cs.setFont(fonts.get(0), size); | |
cs.showText(text); | |
return; | |
} catch (IllegalArgumentException ex) { | |
// do nothing | |
} | |
// now try separately | |
int i = 0; | |
while (i < text.length()) { | |
boolean found = false; | |
for (PDFont font : fonts) { | |
try { | |
String s = text.substring(i, i + 1); | |
font.encode(s); | |
// it works! Try more with this font | |
int j = i + 1; | |
for (; j < text.length(); ++j) { | |
String s2 = text.substring(j, j + 1); | |
if (isWinAnsiEncoding(s2.codePointAt(0)) && font != fonts.get(0)) { | |
// Without this segment, the example would have a flaw: | |
// This code tries to keep the current font, so | |
// the second "abc" would appear in a different font | |
// than the first one, which would be weird. | |
// This segment assumes that the first font has WinAnsiEncoding. | |
// (all static PDType1Font Times / Helvetica / Courier fonts) | |
break; | |
} | |
try { | |
font.encode(s2); | |
} catch (IllegalArgumentException ex) { | |
// it's over | |
break; | |
} | |
} | |
s = text.substring(i, j); | |
cs.setFont(font, size); | |
cs.showText(s); | |
i = j; | |
found = true; | |
break; | |
} catch (IllegalArgumentException ex) { | |
// didn't work, will try next font | |
} | |
} | |
if (!found) { | |
throw new IllegalArgumentException("Could not show '" + text.substring(i, i + 1) + | |
"' with the fonts provided"); | |
} | |
} | |
} | |
private static boolean isWinAnsiEncoding(int unicode) { | |
String name = GlyphList.getAdobeGlyphList().codePointToName(unicode); | |
if (".notdef".equals(name)) { | |
return false; | |
} | |
return WinAnsiEncoding.INSTANCE.contains(name); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment