Skip to content

Fixed ligature bug in PdfToUnicodeCMap #2557

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

Open
swmal wants to merge 1 commit into
base: develop9
Choose a base branch
from
Open

Fixed ligature bug in PdfToUnicodeCMap #2557

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 18 additions & 4 deletions src/EPPlus.Export.Pdf/DocumentObjects/Fonts/PdfToUnicodeCMap.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,10 @@ private string GenerateCMapContent()

private void GenerateCharacterMappings(StringBuilder sb)
{
var sortedMappings = CharacterMappings.OrderBy(kvp => kvp.Key).ToList();
var sortedMappings = CharacterMappings
.Where(kvp => !string.IsNullOrEmpty(kvp.Value))
.OrderBy(kvp => kvp.Key)
.ToList();
var ranges = new List<CharacterRange>();
var individualMappings = new List<CharacterMapping>();
for (int i = 0; i < sortedMappings.Count; i++)
Expand Down Expand Up @@ -143,7 +146,7 @@ private void GenerateCharacterMappings(StringBuilder sb)
// Output ranges
if (ranges.Count > 0)
{
sb.AppendFormat($"{ranges.Count} beginbfrange");
sb.AppendFormat($"{ranges.Count} beginbfrange\n");
foreach (var range in ranges)
{
sb.AppendFormat($"<{FormatCode(range.Start)}> <{FormatCode(range.End)}> <{FormatUnicode(range.UnicodeStart)}>\n");
Expand All @@ -160,14 +163,25 @@ private void GenerateCharacterMappings(StringBuilder sb)
sb.AppendFormat($"{batch.Count} beginbfchar\n");
foreach (var mapping in batch)
{
string hex = ((int)mapping.Unicode[0]).ToString("X4");
sb.AppendFormat($"<{FormatCode(mapping.Code)}> <{hex}>\n");
sb.AppendFormat($"<{FormatCode(mapping.Code)}> <{ToUtf16BeHex(mapping.Unicode)}>\n");
}
sb.Append("endbfchar\n");
}
}
}

private static string ToUtf16BeHex(string text)
{
// .NET strings are already UTF-16, so every char is one UTF-16BE code unit
// and surrogate pairs come out correctly without any special handling.
var sb = new StringBuilder(text.Length * 4);
foreach (char c in text)
{
sb.Append(((int)c).ToString("X4"));
}
return sb.ToString();
}

private bool TryParseSimpleUnicode(string hexString, out int unicodeValue)
{
unicodeValue = 0;
Expand Down
Loading