mirror of
https://github.com/SerenityOS/serenity.git
synced 2025-01-22 09:21:57 -05:00
LibPDF+Clients: Make Document::text_string_to_utf8() return String
It returns UTF-8 text, so make that clear in its return type, and propagate this to clients. No behavior change.
This commit is contained in:
Nico Weber
parent
66378471a0
commit
0d7de7681c
4 changed files with 37 additions and 40 deletions
|
|
@ -60,7 +60,10 @@
|
|||
{
|
||||
if (_groupName)
|
||||
return _groupName;
|
||||
NSString* title = [NSString stringWithUTF8String:_item->title.characters()];
|
||||
|
||||
auto title_view = _item->title.bytes_as_string_view();
|
||||
NSData* title_data = [NSData dataWithBytes:title_view.characters_without_null_termination() length:title_view.length()];
|
||||
NSString* title = [[NSString alloc] initWithData:title_data encoding:NSUTF8StringEncoding];
|
||||
|
||||
// Newlines confuse NSOutlineView, at least in sidebar style (even with `usesSingleLineMode` set to YES on the cell view's text field).
|
||||
title = [[title componentsSeparatedByCharactersInSet:[NSCharacterSet newlineCharacterSet]] componentsJoinedByString:@" "];
|
||||
|
|
|
|||
|
|
@ -509,23 +509,21 @@ ErrorOr<void> PropertiesWindow::create_pdf_tab(GUI::TabWidget& tab_widget, Nonnu
|
|||
if (maybe_info_dict.is_error()) {
|
||||
warnln("Failed to read InfoDict from '{}': {}", m_path, maybe_info_dict.error().message());
|
||||
} else if (maybe_info_dict.value().has_value()) {
|
||||
auto get_info_string = [](PDF::PDFErrorOr<Optional<ByteString>> input) -> ErrorOr<String> {
|
||||
auto get_info_string = []<typename T>(PDF::PDFErrorOr<Optional<T>> input) -> T {
|
||||
if (input.is_error())
|
||||
return String {};
|
||||
if (!input.value().has_value())
|
||||
return String {};
|
||||
return String::from_byte_string(input.value().value());
|
||||
return T {};
|
||||
return input.value().value_or({});
|
||||
};
|
||||
|
||||
auto info_dict = maybe_info_dict.release_value().release_value();
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_title")->set_text(TRY(get_info_string(info_dict.title())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_author")->set_text(TRY(get_info_string(info_dict.author())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_subject")->set_text(TRY(get_info_string(info_dict.subject())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_keywords")->set_text(TRY(get_info_string(info_dict.keywords())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_creator")->set_text(TRY(get_info_string(info_dict.creator())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_producer")->set_text(TRY(get_info_string(info_dict.producer())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_creation_date")->set_text(TRY(get_info_string(info_dict.creation_date())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_modification_date")->set_text(TRY(get_info_string(info_dict.modification_date())));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_title")->set_text(get_info_string(info_dict.title()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_author")->set_text(get_info_string(info_dict.author()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_subject")->set_text(get_info_string(info_dict.subject()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_keywords")->set_text(get_info_string(info_dict.keywords()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_creator")->set_text(get_info_string(info_dict.creator()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_producer")->set_text(get_info_string(info_dict.producer()));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_creation_date")->set_text(TRY(String::from_byte_string((get_info_string(info_dict.creation_date())))));
|
||||
tab.find_descendant_of_type_named<GUI::Label>("pdf_modification_date")->set_text(TRY(String::from_byte_string(get_info_string(info_dict.modification_date()))));
|
||||
}
|
||||
|
||||
return {};
|
||||
|
|
|
|||
|
|
@ -35,32 +35,32 @@ ByteString OutlineItem::to_byte_string(int indent) const
|
|||
return builder.to_byte_string();
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::title() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::title() const
|
||||
{
|
||||
return get_text(CommonNames::Title);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::author() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::author() const
|
||||
{
|
||||
return get_text(CommonNames::Author);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::subject() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::subject() const
|
||||
{
|
||||
return get_text(CommonNames::Subject);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::keywords() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::keywords() const
|
||||
{
|
||||
return get_text(CommonNames::Keywords);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::creator() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::creator() const
|
||||
{
|
||||
return get_text(CommonNames::Creator);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::producer() const
|
||||
PDFErrorOr<Optional<String>> InfoDict::producer() const
|
||||
{
|
||||
return get_text(CommonNames::Producer);
|
||||
}
|
||||
|
|
@ -75,24 +75,20 @@ PDFErrorOr<Optional<ByteString>> InfoDict::modification_date() const
|
|||
return get(CommonNames::ModDate);
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> InfoDict::get_text(DeprecatedFlyString const& name) const
|
||||
PDFErrorOr<Optional<String>> InfoDict::get_text(DeprecatedFlyString const& name) const
|
||||
{
|
||||
return TRY(get(name)).map(Document::text_string_to_utf8);
|
||||
}
|
||||
|
||||
ByteString Document::text_string_to_utf8(ByteString const& text_string)
|
||||
String Document::text_string_to_utf8(ByteString 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_byte_string();
|
||||
}
|
||||
if (text_string.bytes().starts_with(Array<u8, 2> { 0xfe, 0xff }))
|
||||
return TextCodec::decoder_for("utf-16be"sv)->to_utf8(text_string).release_value_but_fixme_should_propagate_errors();
|
||||
|
||||
if (text_string.bytes().starts_with(Array<u8, 3> { 239, 187, 191 })) {
|
||||
// The string is encoded in UTF-8.
|
||||
return text_string.substring(3);
|
||||
}
|
||||
if (text_string.bytes().starts_with(Array<u8, 3> { 239, 187, 191 }))
|
||||
return TextCodec::decoder_for("utf-8"sv)->to_utf8(text_string).release_value_but_fixme_should_propagate_errors();
|
||||
|
||||
return TextCodec::decoder_for("PDFDocEncoding"sv)->to_utf8(text_string).release_value_but_fixme_should_propagate_errors().to_byte_string();
|
||||
return TextCodec::decoder_for("PDFDocEncoding"sv)->to_utf8(text_string).release_value_but_fixme_should_propagate_errors();
|
||||
}
|
||||
|
||||
PDFErrorOr<NonnullRefPtr<Document>> Document::create(ReadonlyBytes bytes)
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ struct OutlineItem final : public RefCounted<OutlineItem>
|
|||
, public Weakable<OutlineItem> {
|
||||
WeakPtr<OutlineItem> parent;
|
||||
Vector<NonnullRefPtr<OutlineItem>> children;
|
||||
ByteString title; // Already converted to UTF-8.
|
||||
String title;
|
||||
i32 count { 0 };
|
||||
Destination dest;
|
||||
Gfx::Color color { Color::NamedColor::Black }; // 'C' in the PDF spec
|
||||
|
|
@ -69,16 +69,16 @@ public:
|
|||
|
||||
// These all return strings that are already converted to UTF-8.
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> title() const;
|
||||
PDFErrorOr<Optional<ByteString>> author() const;
|
||||
PDFErrorOr<Optional<ByteString>> subject() const;
|
||||
PDFErrorOr<Optional<ByteString>> keywords() const;
|
||||
PDFErrorOr<Optional<String>> title() const;
|
||||
PDFErrorOr<Optional<String>> author() const;
|
||||
PDFErrorOr<Optional<String>> subject() const;
|
||||
PDFErrorOr<Optional<String>> keywords() const;
|
||||
|
||||
// Name of the program that created the original, non-PDF file.
|
||||
PDFErrorOr<Optional<ByteString>> creator() const;
|
||||
PDFErrorOr<Optional<String>> creator() const;
|
||||
|
||||
// Name of the program that converted the file to PDF.
|
||||
PDFErrorOr<Optional<ByteString>> producer() const;
|
||||
PDFErrorOr<Optional<String>> producer() const;
|
||||
|
||||
// FIXME: Provide some helper for parsing the date strings returned by these two methods.
|
||||
PDFErrorOr<Optional<ByteString>> creation_date() const;
|
||||
|
|
@ -92,7 +92,7 @@ private:
|
|||
return TRY(m_info_dict->get_string(m_document, name))->string();
|
||||
}
|
||||
|
||||
PDFErrorOr<Optional<ByteString>> get_text(DeprecatedFlyString const& name) const;
|
||||
PDFErrorOr<Optional<String>> get_text(DeprecatedFlyString const& name) const;
|
||||
|
||||
WeakPtr<Document> m_document;
|
||||
NonnullRefPtr<DictObject> m_info_dict;
|
||||
|
|
@ -103,7 +103,7 @@ class Document final
|
|||
, public Weakable<Document> {
|
||||
public:
|
||||
// Converts a text string (PDF 1.7 spec, 3.8.1. "String Types") to UTF-8.
|
||||
static ByteString text_string_to_utf8(ByteString const&);
|
||||
static String text_string_to_utf8(ByteString const&);
|
||||
|
||||
static PDFErrorOr<NonnullRefPtr<Document>> create(ReadonlyBytes bytes);
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue