From 3eaa27f53ad5f6d99e984d693085dce9cf51261b Mon Sep 17 00:00:00 2001
From: Rodrigo Tobar <rtobarc@gmail.com>
Date: Sun, 5 Feb 2023 14:23:07 +0800
Subject: [PATCH] LibPDF: Add infrastructure for accented character glyphs

Type1 accented character glyphs are composed of two other glyphs in the
same font: a base glyph and an accent glyph, given as char codes in the
standard encoding. These two glyphs are then composed together to form
the accented character.

This commit adds the data structures to hold the information for
accented characters, and also the routine that composes the final glyph
path out of the two individual components. All glyphs must have been
loaded by the time this composition takes place, and thus a new
protected consolidate_glyphs() routine has been added to perform this
calculation.
---
 Userland/Libraries/LibPDF/Fonts/CFF.cpp       |  1 +
 .../Libraries/LibPDF/Fonts/PS1FontProgram.cpp |  1 +
 .../LibPDF/Fonts/Type1FontProgram.cpp         | 18 +++++++++++++++
 .../Libraries/LibPDF/Fonts/Type1FontProgram.h | 23 +++++++++++++++++++
 4 files changed, 43 insertions(+)

diff --git a/Userland/Libraries/LibPDF/Fonts/CFF.cpp b/Userland/Libraries/LibPDF/Fonts/CFF.cpp
index eade5fc207..9c8ba8fe9c 100644
--- a/Userland/Libraries/LibPDF/Fonts/CFF.cpp
+++ b/Userland/Libraries/LibPDF/Fonts/CFF.cpp
@@ -116,6 +116,7 @@ PDFErrorOr<NonnullRefPtr<CFF>> CFF::create(ReadonlyBytes const& cff_bytes, RefPt
         auto const& name = charset[i - 1];
         TRY(cff->add_glyph(name, move(glyphs[i])));
     }
+    cff->consolidate_glyphs();
 
     // Encoding given or read
     if (encoding) {
diff --git a/Userland/Libraries/LibPDF/Fonts/PS1FontProgram.cpp b/Userland/Libraries/LibPDF/Fonts/PS1FontProgram.cpp
index 38e87a5b55..5676e5ff9e 100644
--- a/Userland/Libraries/LibPDF/Fonts/PS1FontProgram.cpp
+++ b/Userland/Libraries/LibPDF/Fonts/PS1FontProgram.cpp
@@ -98,6 +98,7 @@ PDFErrorOr<void> PS1FontProgram::parse_encrypted_portion(ByteBuffer const& buffe
         }
     }
 
+    consolidate_glyphs();
     return {};
 }
 
diff --git a/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.cpp b/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.cpp
index 19b6a2075f..649fec3728 100644
--- a/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.cpp
+++ b/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.cpp
@@ -110,6 +110,24 @@ Gfx::AffineTransform Type1FontProgram::glyph_transform_to_device_space(Glyph con
     return transform;
 }
 
+void Type1FontProgram::consolidate_glyphs()
+{
+    for (auto& [name, glyph] : m_glyph_map) {
+        if (!glyph.is_accented_character())
+            continue;
+        auto maybe_base_glyph = m_glyph_map.get(glyph.accented_character().base_character);
+        if (!maybe_base_glyph.has_value())
+            continue;
+        auto glyph_path = maybe_base_glyph.value().path();
+        auto maybe_accent_glyph = m_glyph_map.get(glyph.accented_character().accent_character);
+        if (maybe_accent_glyph.has_value()) {
+            auto path = maybe_accent_glyph.value().path();
+            glyph_path.append_path(move(path));
+        }
+        glyph.path() = glyph_path;
+    }
+}
+
 PDFErrorOr<Type1FontProgram::Glyph> Type1FontProgram::parse_glyph(ReadonlyBytes const& data, Vector<ByteBuffer> const& subroutines, GlyphParserState& state, bool is_type2)
 {
     auto push = [&](float value) -> PDFErrorOr<void> {
diff --git a/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.h b/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.h
index 7509f23be6..c06ed5c2c7 100644
--- a/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.h
+++ b/Userland/Libraries/LibPDF/Fonts/Type1FontProgram.h
@@ -25,6 +25,19 @@ public:
     RefPtr<Encoding> encoding() const { return m_encoding; }
 
 protected:
+    struct AccentedCharacter {
+        AccentedCharacter(u8 base_char_code, u8 accent_char_code, float adx, float ady)
+            : base_character(Encoding::standard_encoding()->get_name(base_char_code))
+            , accent_character(Encoding::standard_encoding()->get_name(accent_char_code))
+            , accent_origin(adx, ady)
+        {
+        }
+
+        DeprecatedFlyString base_character;
+        DeprecatedFlyString accent_character;
+        Gfx::FloatPoint accent_origin;
+    };
+
     class Glyph {
 
     public:
@@ -38,9 +51,17 @@ protected:
         Gfx::Path& path() { return m_path; }
         Gfx::Path const& path() const { return m_path; }
 
+        bool is_accented_character() const { return m_accented_character.has_value(); }
+        AccentedCharacter const& accented_character() const { return m_accented_character.value(); }
+        void set_accented_character(AccentedCharacter&& accented_character)
+        {
+            m_accented_character = move(accented_character);
+        }
+
     private:
         Gfx::Path m_path;
         Optional<float> m_width;
+        Optional<AccentedCharacter> m_accented_character;
     };
 
     struct GlyphParserState {
@@ -86,6 +107,8 @@ protected:
         return {};
     }
 
+    void consolidate_glyphs();
+
 private:
     HashMap<DeprecatedFlyString, Glyph> m_glyph_map;
     Gfx::AffineTransform m_font_matrix;