RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 21:17:44 +00:00
Code Issues Activity Actions

LibPDF: Stop converting encodings in object parser

Browse source 
Per 1.7 spec 3.8.1, there are multiple logical text string types:
* text strings
* ASCII strings
* byte strings

Text strings can be in UTF-16BE, PDFDocEncoding, or (since PDF 2.0)
UTF-8.

But byte strings shouldn't be converted but treated as binary
data.

This makes us no longer convert strings used for drawing page text.
TABLE 5.6 "Text-showing operators" lists the operands for text-showing
operators as just "string", not "text string" (even though these strings
confusingly are called "text strings" in the body text), so not doing
this there is correct (and matches other viewers).

We also no longer incorrectly convert strings used for cypto data
(such as passwords), if they start with an UTF-16BE or UTF-8 marker.

No behavior change for outlines and info dict entries.

https://pdfa.org/understanding-utf-8-in-pdf-2-0/ has a good overview of
this.

(ASCII strings only contain ASCII characters and behave the same
anyways.)
This commit is contained in:
Nico Weber 2023-11-20 21:04:31 -05:00 • committed by Andrew Kaster
parent 8ee0c75f43
commit e39a790c82
3 changed files with 38 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

37
Userland/Libraries/LibPDF/Document.cpp
View file

@ -7,6 +7,7 @@
#include <LibPDF/CommonNames.h>
#include <LibPDF/Document.h>
#include <LibPDF/Parser.h>
#include <LibTextCodec/Decoder.h>
namespace PDF {
@ -36,32 +37,32 @@ DeprecatedString OutlineItem::to_deprecated_string(int indent) const
PDFErrorOr<Optional<DeprecatedString>> InfoDict::title() const
{
return get(CommonNames::Title);
return get_text(CommonNames::Title);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::author() const
{
return get(CommonNames::Author);
return get_text(CommonNames::Author);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::subject() const
{
return get(CommonNames::Subject);
return get_text(CommonNames::Subject);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::keywords() const
{
return get(CommonNames::Keywords);
return get_text(CommonNames::Keywords);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::creator() const
{
return get(CommonNames::Creator);
return get_text(CommonNames::Creator);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::producer() const
{
return get(CommonNames::Producer);
return get_text(CommonNames::Producer);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::creation_date() const
@ -74,6 +75,28 @@ PDFErrorOr<Optional<DeprecatedString>> InfoDict::modification_date() const
return get(CommonNames::ModDate);
}
PDFErrorOr<Optional<DeprecatedString>> InfoDict::get_text(DeprecatedFlyString const& name) const
{
return TRY(get(name)).map(Document::text_string_to_utf8);
}
DeprecatedString Document::text_string_to_utf8(DeprecatedString const& text_string)
{
if (text_string.bytes().starts_with(Array<u8, 2> { 0xfe, 0xff })) {
// The string is encoded in UTF16-BE
return TextCodec::decoder_for("utf-16be"sv)->to_utf8(text_string).release_value_but_fixme_should_propagate_errors().to_deprecated_string();
}
if (text_string.bytes().starts_with(Array<u8, 3> { 239, 187, 191 })) {
// The string is encoded in UTF-8.
return text_string.substring(3);
}
// FIXME: Convert from PDFDocEncoding to UTF-8.
return text_string;
}
PDFErrorOr<NonnullRefPtr<Document>> Document::create(ReadonlyBytes bytes)
{
auto parser = adopt_ref(*new DocumentParser({}, bytes));
@ -544,7 +567,7 @@ PDFErrorOr<NonnullRefPtr<OutlineItem>> Document::build_outline_item(NonnullRefPt
outline_item->children = move(children);
}
outline_item->title = TRY(outline_item_dict->get_string(this, CommonNames::Title))->string();
outline_item->title = text_string_to_utf8(TRY(outline_item_dict->get_string(this, CommonNames::Title))->string());
if (outline_item_dict->contains(CommonNames::Count))
outline_item->count = outline_item_dict->get_value(CommonNames::Count).get<int>();