Skip to content

refactor TextToPDF.call method #388

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
valerybokov wants to merge 2 commits into from
Closed

refactor TextToPDF.call method #388

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ffc6b82
refactor TextToPDF.call method
valerybokov Jan 1, 2026
a6356cf
support UTF8 with BOM and no BOM in TextToPDF.call
valerybokov Jan 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 20 additions & 17 deletions tools/src/main/java/org/apache/pdfbox/tools/TextToPDF.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.BufferedInputStream;
import java.io.InputStreamReader;
import java.io.PrintStream;
import java.io.Reader;
Expand Down Expand Up @@ -185,27 +185,30 @@ public Integer call()
setTopMargin(margins[2]);
setBottomMargin(margins[3]);

boolean hasUtf8BOM = false;
if (charset.equals(StandardCharsets.UTF_8))
try (BufferedInputStream is = new BufferedInputStream(new FileInputStream(infile)))
{
// check for utf8 BOM
// FileInputStream doesn't support mark/reset
try (InputStream is = new FileInputStream(infile))
if (charset.equals(StandardCharsets.UTF_8))
{
if (is.read() == 0xEF && is.read() == 0xBB && is.read() == 0xBF)
final int readLimit = 3;
is.mark(readLimit);

byte[] firstBytes = new byte[readLimit];
if (is.read(firstBytes) != readLimit)
{
hasUtf8BOM = true;
throw new IOException("Could not read 3 bytes, size changed?!");
}
}
}
try (InputStream is = new FileInputStream(infile))
{
if (hasUtf8BOM)
{
long skipped = is.skip(3);
if (skipped != 3)

if (firstBytes[0] == (byte) 0xEF &&
firstBytes[1] == (byte) 0xBB &&
firstBytes[2] == (byte) 0xBF)
{
//UTF-8 with BOM
//3 bytes already read (skipped)
}
else
{
throw new IOException("Could not skip 3 bytes, size changed?!");
//It looks like UTF with no BOM or file was corrupted
is.reset();
}
}
try (Reader reader = new InputStreamReader(is, charset))
Expand Down