use of com.tom_roush.pdfbox.pdmodel.PDDocument in project PdfBox-Android by TomRoush.
the class TestFontEmbedding method testCIDFontType2VerticalSubsetProportional.
/**
* Embed a proportional TTF as vertical CIDFontType2 with subsetting.
*
* @throws IOException
*/
@Test
public void testCIDFontType2VerticalSubsetProportional() throws IOException {
String text = "「ABC」";
String expectedExtractedtext = "「\nA\nB\nC\n」";
File pdf = new File(OUT_DIR, "CIDFontType2VP.pdf");
PDDocument document = new PDDocument();
PDPage page = new PDPage(PDRectangle.A4);
document.addPage(page);
File ipafont = new File("target/fonts/ipagp00303", "ipagp.ttf");
assumeTrue(ipafont.exists());
PDType0Font vfont = PDType0Font.loadVertical(document, ipafont);
PDPageContentStream contentStream = new PDPageContentStream(document, page);
contentStream.beginText();
contentStream.setFont(vfont, 20);
contentStream.newLineAtOffset(50, 700);
contentStream.showText(text);
contentStream.endText();
contentStream.close();
// Check the font substitution
byte[] encode = vfont.encode(text);
int cid = ((encode[0] & 0xFF) << 8) + (encode[1] & 0xFF);
// it's 12461 without substitution
assertEquals(12607, cid);
// Check the dictionaries
COSDictionary fontDict = vfont.getCOSObject();
assertEquals(COSName.IDENTITY_V, fontDict.getDictionaryObject(COSName.ENCODING));
document.save(pdf);
// Vertical metrics are fixed during subsetting, so do this after calling save()
COSDictionary descFontDict = vfont.getDescendantFont().getCOSObject();
COSArray dw2 = (COSArray) descFontDict.getDictionaryObject(COSName.DW2);
// This font uses default values for DW2
assertNull(dw2);
// c [ w1_1y v_1x v_1y ... w1_ny v_nx v_ny ]
COSArray w2 = (COSArray) descFontDict.getDictionaryObject(COSName.W2);
assertEquals(2, w2.size());
// Start CID
assertEquals(12607, w2.getInt(0));
COSArray metrics = (COSArray) w2.getObject(1);
int i = 0;
for (int n : new int[] { -570, 500, 450, -570, 500, 880 }) {
assertEquals(n, metrics.getInt(i++));
}
document.close();
// Check text extraction
String extracted = getUnicodeText(pdf);
assertEquals(expectedExtractedtext, extracted.replaceAll("\r", "").trim());
}
use of com.tom_roush.pdfbox.pdmodel.PDDocument in project PdfBox-Android by TomRoush.
the class TestFontEmbedding method testCIDFontType2VerticalSubsetMonospace.
/**
* Embed a monospace TTF as vertical CIDFontType2 with subsetting.
*
* @throws IOException
*/
@Test
public void testCIDFontType2VerticalSubsetMonospace() throws IOException {
String text = "「ABC」";
String expectedExtractedtext = "「\nA\nB\nC\n」";
File pdf = new File(OUT_DIR, "CIDFontType2VM.pdf");
PDDocument document = new PDDocument();
PDPage page = new PDPage(PDRectangle.A4);
document.addPage(page);
File ipafont = new File("target/fonts/ipag00303", "ipag.ttf");
assumeTrue(ipafont.exists());
PDType0Font vfont = PDType0Font.loadVertical(document, ipafont);
PDPageContentStream contentStream = new PDPageContentStream(document, page);
contentStream.beginText();
contentStream.setFont(vfont, 20);
contentStream.newLineAtOffset(50, 700);
contentStream.showText(text);
contentStream.endText();
contentStream.close();
// Check the font substitution
byte[] encode = vfont.encode(text);
int cid = ((encode[0] & 0xFF) << 8) + (encode[1] & 0xFF);
// it's 441 without substitution
assertEquals(7392, cid);
// Check the dictionaries
COSDictionary fontDict = vfont.getCOSObject();
assertEquals(COSName.IDENTITY_V, fontDict.getDictionaryObject(COSName.ENCODING));
document.save(pdf);
// Vertical metrics are fixed during subsetting, so do this after calling save()
COSDictionary descFontDict = vfont.getDescendantFont().getCOSObject();
COSArray dw2 = (COSArray) descFontDict.getDictionaryObject(COSName.DW2);
// This font uses default values for DW2
assertNull(dw2);
COSArray w2 = (COSArray) descFontDict.getDictionaryObject(COSName.W2);
// Monospaced font has no entries
assertEquals(0, w2.size());
document.close();
// Check text extraction
String extracted = getUnicodeText(pdf);
assertEquals(expectedExtractedtext, extracted.replaceAll("\r", "").trim());
}
use of com.tom_roush.pdfbox.pdmodel.PDDocument in project PdfBox-Android by TomRoush.
the class TestFontEmbedding method getUnicodeText.
private String getUnicodeText(File file) throws IOException {
PDDocument document = PDDocument.load(file);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(document);
}
use of com.tom_roush.pdfbox.pdmodel.PDDocument in project PdfBox-Android by TomRoush.
the class TestFontEmbedding method validateCIDFontType2.
private void validateCIDFontType2(boolean useSubset) throws Exception {
PDDocument document = new PDDocument();
PDPage page = new PDPage(PDRectangle.A4);
document.addPage(page);
InputStream input = PDFont.class.getResourceAsStream("/com/tom_roush/pdfbox/resources/ttf/LiberationSans-Regular.ttf");
PDType0Font font = PDType0Font.load(document, input, useSubset);
PDPageContentStream stream = new PDPageContentStream(document, page);
stream.beginText();
stream.setFont(font, 12);
String text = "Unicode русский язык Tiếng Việt";
stream.newLineAtOffset(50, 600);
stream.showText(text);
stream.endText();
stream.close();
File file = new File(OUT_DIR, "CIDFontType2.pdf");
document.save(file);
document.close();
// check that the extracted text matches what we wrote
String extracted = getUnicodeText(file);
assertEquals(text, extracted.trim());
}
use of com.tom_roush.pdfbox.pdmodel.PDDocument in project PdfBox-Android by TomRoush.
the class PDTextFieldTest method setUp.
@Before
public void setUp() {
document = new PDDocument();
acroForm = new PDAcroForm(document);
}
Aggregations