LibPDF: Implement name tree lookups

Name Trees are hierarchical, string-keyed, sorted-by-key dictionary
structures in PDF where each node (except the root) specifies the bounds
of the values it holds, and either its kids (more nodes) or the
key/value pairs it contains.

This commit implements a series of lookup calls for finding a key in
such name trees. This implementation follows the tree as needed on each
lookup, but if that becomes inefficient in the long run we can switch to
creating a HashMap with all the contents, which as a drawback will
require more memory.

3 files changed, 46 insertions, 0 deletions

diff --git a/Userland/Libraries/LibPDF/CommonNames.h b/Userland/Libraries/LibPDF/CommonNames.h
index 85f878c4be..a3832ba2b3 100644
--- a/Userland/Libraries/LibPDF/CommonNames.h
+++ b/Userland/Libraries/LibPDF/CommonNames.h
@@ -93,12 +93,14 @@
     A(Length1)                    \
     A(Length2)                    \
     A(Length3)                    \
+    A(Limits)                     \
     A(Linearized)                 \
     A(ML)                         \
     A(Matrix)                     \
     A(MediaBox)                   \
     A(MissingWidth)               \
     A(N)                          \
+    A(Names)                      \
     A(Next)                       \
     A(O)                          \
     A(OP)                         \
diff --git a/Userland/Libraries/LibPDF/Document.cpp b/Userland/Libraries/LibPDF/Document.cpp
index a8f85e8a23..acc43ef192 100644
--- a/Userland/Libraries/LibPDF/Document.cpp
+++ b/Userland/Libraries/LibPDF/Document.cpp
@@ -199,6 +199,46 @@ PDFErrorOr<void> Document::add_page_tree_node_to_page_tree(NonnullRefPtr<DictObj
     return {};
 }
 
+PDFErrorOr<NonnullRefPtr<Object>> Document::find_in_name_tree(NonnullRefPtr<DictObject> tree, FlyString name)
+{
+    if (tree->contains(CommonNames::Kids)) {
+        return find_in_name_tree_nodes(tree->get_array(CommonNames::Kids), name);
+    }
+    if (!tree->contains(CommonNames::Names))
+        return Error { Error::Type::MalformedPDF, "name tree has neither Kids nor Names" };
+    auto key_value_names_array = TRY(tree->get_array(this, CommonNames::Names));
+    return find_in_key_value_array(key_value_names_array, name);
+}
+
+PDFErrorOr<NonnullRefPtr<Object>> Document::find_in_name_tree_nodes(NonnullRefPtr<ArrayObject> siblings, FlyString name)
+{
+    for (size_t i = 0; i < siblings->size(); i++) {
+        auto sibling = TRY(resolve_to<DictObject>(siblings->at(i)));
+        auto limits = sibling->get_array(CommonNames::Limits);
+        if (limits->size() != 2)
+            return Error { Error::Type::MalformedPDF, "Expected 2-element Limits array" };
+        auto start = limits->get_string_at(0);
+        auto end = limits->get_string_at(1);
+        if (start->string() <= name && end->string() >= name) {
+            return find_in_name_tree(sibling, name);
+        }
+    }
+    return Error { Error::Type::MalformedPDF, DeprecatedString::formatted("Didn't find node in name tree containing name {}", name) };
+}
+
+PDFErrorOr<NonnullRefPtr<Object>> Document::find_in_key_value_array(NonnullRefPtr<ArrayObject> key_value_array, FlyString name)
+{
+    if (key_value_array->size() % 2 == 1)
+        return Error { Error::Type::MalformedPDF, "key/value array has dangling key" };
+    for (size_t i = 0; i < key_value_array->size() / 2; i++) {
+        auto key = key_value_array->get_string_at(2 * i);
+        if (key->string() == name) {
+            return key_value_array->get_object_at(this, 2 * i + 1);
+        }
+    }
+    return Error { Error::Type::MalformedPDF, DeprecatedString::formatted("Didn't find expected name {} in key/value array", name) };
+}
+
 PDFErrorOr<void> Document::build_outline()
 {
     if (!m_catalog->contains(CommonNames::Outlines))
diff --git a/Userland/Libraries/LibPDF/Document.h b/Userland/Libraries/LibPDF/Document.h
index 7557f677ea..3b183ceab9 100644
--- a/Userland/Libraries/LibPDF/Document.h
+++ b/Userland/Libraries/LibPDF/Document.h
@@ -139,6 +139,10 @@ private:
 
     PDFErrorOr<NonnullRefPtr<Object>> get_inheritable_object(FlyString const& name, NonnullRefPtr<DictObject>);
 
+    PDFErrorOr<NonnullRefPtr<Object>> find_in_name_tree(NonnullRefPtr<DictObject> root, FlyString name);
+    PDFErrorOr<NonnullRefPtr<Object>> find_in_name_tree_nodes(NonnullRefPtr<ArrayObject> siblings, FlyString name);
+    PDFErrorOr<NonnullRefPtr<Object>> find_in_key_value_array(NonnullRefPtr<ArrayObject> key_value_array, FlyString name);
+
     NonnullRefPtr<DocumentParser> m_parser;
     RefPtr<DictObject> m_catalog;
     RefPtr<DictObject> m_trailer;