LibWeb: Move initial creation of Unicode segmenters to the Document

The expensive part of creating a segmenter is doing the locale and UCD
data lookups at creation time. Instead of doing this once per text node,
cache the segmenters on the document, and clone them as needed (cloning
is much, much cheaper).

On a profile loading Ladybird's GitHub repo, the following hot methods
changed as follows:

    ChunkIterator ctor: 6.08% -> 0.21%
    Segmenter factory:  5.86% ->    0%
    Segmenter clone:    N/A   -> 0.09%

Userland/Libraries/LibWeb/DOM/CharacterData.cpp

@@ -157,20 +157,20 @@ WebIDL::ExceptionOr<void> CharacterData::delete_data(size_t offset, size_t count
     return replace_data(offset, count, String {});
 }
 
-Unicode::Segmenter& CharacterData::grapheme_segmenter()
+Unicode::Segmenter& CharacterData::grapheme_segmenter() const
 {
     if (!m_grapheme_segmenter) {
-        m_grapheme_segmenter = Unicode::Segmenter::create(Unicode::SegmenterGranularity::Grapheme);
+        m_grapheme_segmenter = document().grapheme_segmenter().clone();
         m_grapheme_segmenter->set_segmented_text(m_data);
     }
 
     return *m_grapheme_segmenter;
 }
 
-Unicode::Segmenter& CharacterData::word_segmenter()
+Unicode::Segmenter& CharacterData::word_segmenter() const
 {
     if (!m_word_segmenter) {
-        m_word_segmenter = Unicode::Segmenter::create(Unicode::SegmenterGranularity::Word);
+        m_word_segmenter = document().word_segmenter().clone();
         m_word_segmenter->set_segmented_text(m_data);
     }
 

Userland/Libraries/LibWeb/DOM/CharacterData.h

@@ -40,8 +40,8 @@ public:
     WebIDL::ExceptionOr<void> delete_data(size_t offset_in_utf16_code_units, size_t count_in_utf16_code_units);
     WebIDL::ExceptionOr<void> replace_data(size_t offset_in_utf16_code_units, size_t count_in_utf16_code_units, String const&);
 
-    Unicode::Segmenter& grapheme_segmenter();
-    Unicode::Segmenter& word_segmenter();
+    Unicode::Segmenter& grapheme_segmenter() const;
+    Unicode::Segmenter& word_segmenter() const;
 
 protected:
     CharacterData(Document&, NodeType, String const&);
@@ -51,8 +51,8 @@ protected:
 private:
     String m_data;
 
-    OwnPtr<Unicode::Segmenter> m_grapheme_segmenter;
-    OwnPtr<Unicode::Segmenter> m_word_segmenter;
+    mutable OwnPtr<Unicode::Segmenter> m_grapheme_segmenter;
+    mutable OwnPtr<Unicode::Segmenter> m_word_segmenter;
 };
 
 }

Userland/Libraries/LibWeb/DOM/Document.cpp

@@ -18,6 +18,7 @@
 #include <LibJS/Runtime/Array.h>
 #include <LibJS/Runtime/FunctionObject.h>
 #include <LibJS/Runtime/NativeFunction.h>
+#include <LibUnicode/Segmenter.h>
 #include <LibWeb/Animations/Animation.h>
 #include <LibWeb/Animations/AnimationPlaybackEvent.h>
 #include <LibWeb/Animations/AnimationTimeline.h>
@@ -5606,4 +5607,18 @@ RefPtr<Painting::DisplayList> Document::record_display_list(PaintConfig config)
     return display_list;
 }
 
+Unicode::Segmenter& Document::grapheme_segmenter() const
+{
+    if (!m_grapheme_segmenter)
+        m_grapheme_segmenter = Unicode::Segmenter::create(Unicode::SegmenterGranularity::Grapheme);
+    return *m_grapheme_segmenter;
+}
+
+Unicode::Segmenter& Document::word_segmenter() const
+{
+    if (!m_word_segmenter)
+        m_word_segmenter = Unicode::Segmenter::create(Unicode::SegmenterGranularity::Word);
+    return *m_word_segmenter;
+}
+
 }

Userland/Libraries/LibWeb/DOM/Document.h

@@ -19,6 +19,7 @@
 #include <LibJS/Console.h>
 #include <LibJS/Forward.h>
 #include <LibURL/URL.h>
+#include <LibUnicode/Forward.h>
 #include <LibWeb/CSS/CSSStyleSheet.h>
 #include <LibWeb/CSS/StyleSheetList.h>
 #include <LibWeb/Cookie/Cookie.h>
@@ -720,6 +721,9 @@ public:
 
     void invalidate_display_list();
 
+    Unicode::Segmenter& grapheme_segmenter() const;
+    Unicode::Segmenter& word_segmenter() const;
+
 protected:
     virtual void initialize(JS::Realm&) override;
     virtual void visit_edges(Cell::Visitor&) override;
@@ -998,6 +1002,9 @@ private:
 
     Optional<PaintConfig> m_cached_display_list_paint_config;
     RefPtr<Painting::DisplayList> m_cached_display_list;
+
+    mutable OwnPtr<Unicode::Segmenter> m_grapheme_segmenter;
+    mutable OwnPtr<Unicode::Segmenter> m_word_segmenter;
 };
 
 template<>

Userland/Libraries/LibWeb/Layout/InlineLevelIterator.cpp

@@ -357,7 +357,7 @@ void InlineLevelIterator::enter_text_node(Layout::TextNode const& text_node)
         .do_respect_linebreaks = do_respect_linebreaks,
         .is_first_chunk = true,
         .is_last_chunk = false,
-        .chunk_iterator = TextNode::ChunkIterator { text_node.text_for_rendering(), do_wrap_lines, do_respect_linebreaks, text_node.computed_values().font_list() },
+        .chunk_iterator = TextNode::ChunkIterator { text_node, do_wrap_lines, do_respect_linebreaks },
     };
 }
 

Userland/Libraries/LibWeb/Layout/TextNode.cpp

@@ -391,14 +391,23 @@ void TextNode::compute_text_for_rendering()
     m_text_for_rendering = MUST(builder.to_string());
 }
 
-TextNode::ChunkIterator::ChunkIterator(String const& text, bool wrap_lines, bool respect_linebreaks, Gfx::FontCascadeList const& font_cascade_list)
+Unicode::Segmenter& TextNode::grapheme_segmenter() const
+{
+    if (!m_grapheme_segmenter) {
+        m_grapheme_segmenter = document().grapheme_segmenter().clone();
+        m_grapheme_segmenter->set_segmented_text(text_for_rendering());
+    }
+
+    return *m_grapheme_segmenter;
+}
+
+TextNode::ChunkIterator::ChunkIterator(TextNode const& text_node, bool wrap_lines, bool respect_linebreaks)
     : m_wrap_lines(wrap_lines)
     , m_respect_linebreaks(respect_linebreaks)
-    , m_utf8_view(text)
-    , m_font_cascade_list(font_cascade_list)
-    , m_segmenter(Unicode::Segmenter::create(Unicode::SegmenterGranularity::Grapheme))
+    , m_utf8_view(text_node.text_for_rendering())
+    , m_font_cascade_list(text_node.computed_values().font_list())
+    , m_grapheme_segmenter(text_node.grapheme_segmenter())
 {
-    m_segmenter->set_segmented_text(text);
 }
 
 static Gfx::GlyphRun::TextType text_type_for_code_point(u32 code_point)
@@ -470,7 +479,7 @@ Optional<TextNode::Chunk> TextNode::ChunkIterator::next_without_peek()
         return *m_utf8_view.iterator_at_byte_offset_without_validation(m_current_index);
     };
     auto next_grapheme_boundary = [this]() {
-        return m_segmenter->next_boundary(m_current_index).value_or(m_utf8_view.byte_length());
+        return m_grapheme_segmenter.next_boundary(m_current_index).value_or(m_utf8_view.byte_length());
     };
 
     auto code_point = current_code_point();

Userland/Libraries/LibWeb/Layout/TextNode.h

@@ -39,7 +39,7 @@ public:
 
     class ChunkIterator {
     public:
-        ChunkIterator(String const& text, bool wrap_lines, bool respect_linebreaks, Gfx::FontCascadeList const&);
+        ChunkIterator(TextNode const&, bool wrap_lines, bool respect_linebreaks);
 
         Optional<Chunk> next();
         Optional<Chunk> peek(size_t);
@@ -53,7 +53,7 @@ public:
         Utf8View m_utf8_view;
         Gfx::FontCascadeList const& m_font_cascade_list;
 
-        NonnullOwnPtr<Unicode::Segmenter> m_segmenter;
+        Unicode::Segmenter& m_grapheme_segmenter;
         size_t m_current_index { 0 };
 
         Vector<Chunk> m_peek_queue;
@@ -62,12 +62,15 @@ public:
     void invalidate_text_for_rendering();
     void compute_text_for_rendering();
 
+    Unicode::Segmenter& grapheme_segmenter() const;
+
     virtual JS::GCPtr<Painting::Paintable> create_paintable() const override;
 
 private:
     virtual bool is_text_node() const final { return true; }
 
     Optional<String> m_text_for_rendering;
+    mutable OwnPtr<Unicode::Segmenter> m_grapheme_segmenter;
 };
 
 template<>

Userland/Libraries/LibWeb/Page/EventHandler.cpp

@@ -1225,7 +1225,7 @@ void EventHandler::update_selection_range_for_input_or_textarea()
 Unicode::Segmenter& EventHandler::word_segmenter()
 {
     if (!m_word_segmenter)
-        m_word_segmenter = Unicode::Segmenter::create(Unicode::SegmenterGranularity::Word);
+        m_word_segmenter = m_navigable->active_document()->word_segmenter().clone();
     return *m_word_segmenter;
 }