mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-26 09:30:24 +00:00
8c745ad0d9
This commit introduces the ability to parse the document catalog dict, as well as the page tree and individual pages. Pages obviously aren't fully parsed, as we won't care about most of the fields until we start actually rendering PDFs. One of the primary benefits of the PDF format is laziness. PDFs are not meant to be parsed all at once, and the same is true for pages. When a Document is constructed, it builds a map of page number to object index, but it does not fetch and parse any of the pages. A page is only parsed when a caller requests that particular page (and is cached going forwards). Additionally, this commit also adds an object_cast function which logs bad casts if DEBUG_PDF is set. Additionally, utility functions were added to ArrayObject and DictObject to get all types of objects from the collections to avoid having to manually cast.
140 lines
4.1 KiB
C++
140 lines
4.1 KiB
C++
/*
|
|
* Copyright (c) 2021, Matthew Olsson <mattco@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#include <AK/Hex.h>
|
|
#include <LibPDF/Document.h>
|
|
#include <LibPDF/Object.h>
|
|
|
|
namespace PDF {
|
|
|
|
NonnullRefPtr<Object> ArrayObject::get_object_at(Document* document, size_t index) const
|
|
{
|
|
return document->resolve_to<Object>(m_elements[index]);
|
|
}
|
|
|
|
NonnullRefPtr<Object> DictObject::get_object(Document* document, const FlyString& key) const
|
|
{
|
|
return document->resolve_to<Object>(get_value(key));
|
|
}
|
|
|
|
#define DEFINE_ACCESSORS(class_name, snake_name) \
|
|
NonnullRefPtr<class_name> ArrayObject::get_##snake_name##_at(Document* document, size_t index) const \
|
|
{ \
|
|
return document->resolve_to<class_name>(m_elements[index]); \
|
|
} \
|
|
\
|
|
NonnullRefPtr<class_name> DictObject::get_##snake_name(Document* document, const FlyString& key) const \
|
|
{ \
|
|
return document->resolve_to<class_name>(get(key).value()); \
|
|
}
|
|
ENUMERATE_DIRECT_OBJECT_TYPES(DEFINE_ACCESSORS)
|
|
#undef DEFINE_INDEXER
|
|
|
|
static void append_indent(StringBuilder& builder, int indent)
|
|
{
|
|
for (int i = 0; i < indent; i++)
|
|
builder.append(" ");
|
|
}
|
|
|
|
String StringObject::to_string(int) const
|
|
{
|
|
if (is_binary())
|
|
return String::formatted("<{}>", encode_hex(string().bytes()).to_uppercase());
|
|
return String::formatted("({})", string());
|
|
}
|
|
|
|
String NameObject::to_string(int) const
|
|
{
|
|
StringBuilder builder;
|
|
builder.appendff("/{}", this->name());
|
|
return builder.to_string();
|
|
}
|
|
|
|
String ArrayObject::to_string(int indent) const
|
|
{
|
|
StringBuilder builder;
|
|
builder.append("[\n");
|
|
bool first = true;
|
|
|
|
for (auto& element : elements()) {
|
|
if (!first)
|
|
builder.append(",\n");
|
|
first = false;
|
|
append_indent(builder, indent + 1);
|
|
builder.appendff("{}", element.to_string(indent));
|
|
}
|
|
|
|
builder.append('\n');
|
|
append_indent(builder, indent);
|
|
builder.append(']');
|
|
return builder.to_string();
|
|
}
|
|
|
|
String DictObject::to_string(int indent) const
|
|
{
|
|
StringBuilder builder;
|
|
builder.append("<<\n");
|
|
bool first = true;
|
|
|
|
for (auto& [key, value] : map()) {
|
|
if (!first)
|
|
builder.append(",\n");
|
|
first = false;
|
|
append_indent(builder, indent + 1);
|
|
builder.appendff("/{} ", key);
|
|
builder.appendff("{}", value.to_string(indent + 1));
|
|
}
|
|
|
|
builder.append('\n');
|
|
append_indent(builder, indent);
|
|
builder.append(">>");
|
|
return builder.to_string();
|
|
}
|
|
|
|
String StreamObject::to_string(int indent) const
|
|
{
|
|
StringBuilder builder;
|
|
builder.append("stream\n");
|
|
append_indent(builder, indent);
|
|
builder.appendff("{}\n", dict()->to_string(indent + 1));
|
|
append_indent(builder, indent + 1);
|
|
|
|
auto string = encode_hex(bytes());
|
|
while (true) {
|
|
if (string.length() > 60) {
|
|
builder.appendff("{}\n", string.substring(0, 60));
|
|
append_indent(builder, indent);
|
|
string = string.substring(60);
|
|
continue;
|
|
}
|
|
|
|
builder.appendff("{}\n", string);
|
|
break;
|
|
}
|
|
|
|
append_indent(builder, indent);
|
|
builder.append("endstream");
|
|
return builder.to_string();
|
|
}
|
|
|
|
String IndirectValue::to_string(int indent) const
|
|
{
|
|
StringBuilder builder;
|
|
builder.appendff("{} {} obj\n", index(), generation_index());
|
|
append_indent(builder, indent + 1);
|
|
builder.append(value().to_string(indent + 1));
|
|
builder.append('\n');
|
|
append_indent(builder, indent);
|
|
builder.append("endobj");
|
|
return builder.to_string();
|
|
}
|
|
|
|
String IndirectValueRef::to_string(int) const
|
|
{
|
|
return String::formatted("{} {} R", index(), generation_index());
|
|
}
|
|
|
|
}
|