lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-10-14 19:05:01 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

handle type 1 font with no descriptor information #132

Browse Source 
though required by the spec an adobe type 1 font may be missing all width data. in this case we default to empty values and treat it like a normal adobe type 1 font.
This commit is contained in:
Eliot Jones
2020-02-05 10:46:39 +00:00
parent 10ca77a034
commit 40dc80c281
1 changed files with 28 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/UglyToad.PdfPig/PdfFonts/Parser/Handlers/Type1FontHandler.cs
View File

@@ -23,8 +23,8 @@
private readonly FontDescriptorFactory fontDescriptorFactory; private readonly FontDescriptorFactory fontDescriptorFactory;
private readonly IEncodingReader encodingReader; private readonly IEncodingReader encodingReader;
public Type1FontHandler(IPdfTokenScanner pdfScanner, IFilterProvider filterProvider, public Type1FontHandler(IPdfTokenScanner pdfScanner, IFilterProvider filterProvider,
FontDescriptorFactory fontDescriptorFactory, FontDescriptorFactory fontDescriptorFactory,
IEncodingReader encodingReader) IEncodingReader encodingReader)
{ {
this.pdfScanner = pdfScanner; this.pdfScanner = pdfScanner;
@@ -40,7 +40,7 @@
if (usingStandard14Only) if (usingStandard14Only)
{ {
// TODO: some fonts combine standard 14 font with other metrics. // TODO: some fonts combine standard 14 font with other metrics.
if (!dictionary.TryGet(NameToken.BaseFont, out var baseFontToken) if (!dictionary.TryGet(NameToken.BaseFont, out var baseFontToken)
|| !(baseFontToken is NameToken standard14Name)) || !(baseFontToken is NameToken standard14Name))
{ {
throw new InvalidFontFormatException($"The Type 1 font did not contain a first character entry but also did not reference a standard 14 font: {dictionary}"); throw new InvalidFontFormatException($"The Type 1 font did not contain a first character entry but also did not reference a standard 14 font: {dictionary}");
@@ -48,20 +48,34 @@
var metrics = Standard14.GetAdobeFontMetrics(standard14Name.Data); var metrics = Standard14.GetAdobeFontMetrics(standard14Name.Data);
var overrideEncoding = encodingReader.Read(dictionary, isLenientParsing); if (metrics != null)
{
var overrideEncoding = encodingReader.Read(dictionary, isLenientParsing);
return new Type1Standard14Font(metrics, overrideEncoding); return new Type1Standard14Font(metrics, overrideEncoding);
}
} }
var firstCharacter = FontDictionaryAccessHelper.GetFirstCharacter(dictionary); int firstCharacter, lastCharacter;
double[] widths;
if (!usingStandard14Only)
{
firstCharacter = FontDictionaryAccessHelper.GetFirstCharacter(dictionary);
var lastCharacter = FontDictionaryAccessHelper.GetLastCharacter(dictionary); lastCharacter = FontDictionaryAccessHelper.GetLastCharacter(dictionary);
var widths = FontDictionaryAccessHelper.GetWidths(pdfScanner, dictionary, isLenientParsing); widths = FontDictionaryAccessHelper.GetWidths(pdfScanner, dictionary, isLenientParsing);
}
else
{
firstCharacter = 0;
lastCharacter = 0;
widths = EmptyArray<double>.Instance;
}
if (!dictionary.TryGet(NameToken.FontDescriptor, out var _)) if (!dictionary.TryGet(NameToken.FontDescriptor, out var _))
{ {
if (dictionary.TryGet(NameToken.BaseFont, out var baseFontToken) && if (dictionary.TryGet(NameToken.BaseFont, out var baseFontToken) &&
DirectObjectFinder.TryGet(baseFontToken, pdfScanner, out NameToken baseFontName)) DirectObjectFinder.TryGet(baseFontToken, pdfScanner, out NameToken baseFontName))
{ {
var metrics = Standard14.GetAdobeFontMetrics(baseFontName.Data); var metrics = Standard14.GetAdobeFontMetrics(baseFontName.Data);
@@ -77,7 +91,7 @@
var font = ParseFontProgram(descriptor, isLenientParsing); var font = ParseFontProgram(descriptor, isLenientParsing);
var name = FontDictionaryAccessHelper.GetName(pdfScanner, dictionary, descriptor, isLenientParsing); var name = FontDictionaryAccessHelper.GetName(pdfScanner, dictionary, descriptor, isLenientParsing);
CMap toUnicodeCMap = null; CMap toUnicodeCMap = null;
if (dictionary.TryGet(NameToken.ToUnicode, out var toUnicodeObj)) if (dictionary.TryGet(NameToken.ToUnicode, out var toUnicodeObj))
{ {
@@ -105,7 +119,7 @@
if (encoding == null) if (encoding == null)
{ {
font?.Match(x => encoding = new BuiltInEncoding(x.Encoding), _ => {}); font?.Match(x => encoding = new BuiltInEncoding(x.Encoding), _ => { });
} }
return new Type1FontSimple(name, firstCharacter, lastCharacter, widths, descriptor, encoding, toUnicodeCMap, font); return new Type1FontSimple(name, firstCharacter, lastCharacter, widths, descriptor, encoding, toUnicodeCMap, font);
@@ -122,7 +136,7 @@
{ {
return null; return null;
} }
try try
{ {
if (!(pdfScanner.Get(descriptor.FontFile.ObjectKey.Data).Data is StreamToken stream)) if (!(pdfScanner.Get(descriptor.FontFile.ObjectKey.Data).Data is StreamToken stream))
@@ -139,10 +153,10 @@
var cffFont = CompactFontFormatParser.Parse(new CompactFontFormatData(bytes)); var cffFont = CompactFontFormatParser.Parse(new CompactFontFormatData(bytes));
return Union<Type1Font, CompactFontFormatFontCollection>.Two(cffFont); return Union<Type1Font, CompactFontFormatFontCollection>.Two(cffFont);
} }
var length1 = stream.StreamDictionary.Get<NumericToken>(NameToken.Length1, pdfScanner); var length1 = stream.StreamDictionary.Get<NumericToken>(NameToken.Length1, pdfScanner);
var length2 = stream.StreamDictionary.Get<NumericToken>(NameToken.Length2, pdfScanner); var length2 = stream.StreamDictionary.Get<NumericToken>(NameToken.Length2, pdfScanner);
var font = Type1FontParser.Parse(new ByteArrayInputBytes(bytes), length1.Int, length2.Int); var font = Type1FontParser.Parse(new ByteArrayInputBytes(bytes), length1.Int, length2.Int);
return Union<Type1Font, CompactFontFormatFontCollection>.One(font); return Union<Type1Font, CompactFontFormatFontCollection>.One(font);