From eac2b2382c36771cb62bb4beaf18dfc2e018b18f Mon Sep 17 00:00:00 2001
From: Nico Weber <thakis@chromium.org>
Date: Tue, 24 Jan 2023 08:50:53 -0500
Subject: [PATCH] LibTextCodec: Add a MacRoman decoder

Allows displaying `<meta charset="x-mac-roman">` html files.
(`:set fenc=macroman`, `:w` in vim to save in that encoding.)
---
 Userland/Libraries/LibTextCodec/Decoder.cpp | 28 +++++++++++++++++++++
 Userland/Libraries/LibTextCodec/Decoder.h   |  5 ++++
 2 files changed, 33 insertions(+)

diff --git a/Userland/Libraries/LibTextCodec/Decoder.cpp b/Userland/Libraries/LibTextCodec/Decoder.cpp
index 4c6b2fbfb7..d991528593 100644
--- a/Userland/Libraries/LibTextCodec/Decoder.cpp
+++ b/Userland/Libraries/LibTextCodec/Decoder.cpp
@@ -25,6 +25,7 @@ HebrewDecoder s_hebrew_decoder;
 CyrillicDecoder s_cyrillic_decoder;
 Koi8RDecoder s_koi8r_decoder;
 Latin9Decoder s_latin9_decoder;
+MacRomanDecoder s_mac_roman_decoder;
 TurkishDecoder s_turkish_decoder;
 XUserDefinedDecoder s_x_user_defined_decoder;
 }
@@ -51,6 +52,8 @@ Decoder* decoder_for(DeprecatedString const& a_encoding)
             return &s_koi8r_decoder;
         if (encoding.value().equals_ignoring_case("iso-8859-15"sv))
             return &s_latin9_decoder;
+        if (encoding.value().equals_ignoring_case("macintosh"sv))
+            return &s_mac_roman_decoder;
         if (encoding.value().equals_ignoring_case("windows-1254"sv))
             return &s_turkish_decoder;
         if (encoding.value().equals_ignoring_case("x-user-defined"sv))
@@ -528,6 +531,31 @@ void Latin9Decoder::process(StringView input, Function<void(u32)> on_code_point)
     }
 }
 
+void MacRomanDecoder::process(StringView input, Function<void(u32)> on_code_point)
+{
+    // https://encoding.spec.whatwg.org/index-macintosh.txt
+    // clang-format off
+    static constexpr Array<u32, 128> translation_table = {
+        0x00C4, 0x00C5, 0x00C7, 0x00C9, 0x00D1, 0x00D6, 0x00DC, 0x00E1, 0x00E0, 0x00E2, 0x00E4, 0x00E3, 0x00E5, 0x00E7, 0x00E9, 0x00E8,
+        0x00EA, 0x00EB, 0x00ED, 0x00EC, 0x00EE, 0x00EF, 0x00F1, 0x00F3, 0x00F2, 0x00F4, 0x00F6, 0x00F5, 0x00FA, 0x00F9, 0x00FB, 0x00FC,
+        0x2020, 0x00B0, 0x00A2, 0x00A3, 0x00A7, 0x2022, 0x00B6, 0x00DF, 0x00AE, 0x00A9, 0x2122, 0x00B4, 0x00A8, 0x2260, 0x00C6, 0x00D8,
+        0x221E, 0x00B1, 0x2264, 0x2265, 0x00A5, 0x00B5, 0x2202, 0x2211, 0x220F, 0x03C0, 0x222B, 0x00AA, 0x00BA, 0x03A9, 0x00E6, 0x00F8,
+        0x00BF, 0x00A1, 0x00AC, 0x221A, 0x0192, 0x2248, 0x2206, 0x00AB, 0x00BB, 0x2026, 0x00A0, 0x00C0, 0x00C3, 0x00D5, 0x0152, 0x0153,
+        0x2013, 0x2014, 0x201C, 0x201D, 0x2018, 0x2019, 0x00F7, 0x25CA, 0x00FF, 0x0178, 0x2044, 0x20AC, 0x2039, 0x203A, 0xFB01, 0xFB02,
+        0x2021, 0x00B7, 0x201A, 0x201E, 0x2030, 0x00C2, 0x00CA, 0x00C1, 0x00CB, 0x00C8, 0x00CD, 0x00CE, 0x00CF, 0x00CC, 0x00D3, 0x00D4,
+        0xF8FF, 0x00D2, 0x00DA, 0x00DB, 0x00D9, 0x0131, 0x02C6, 0x02DC, 0x00AF, 0x02D8, 0x02D9, 0x02DA, 0x00B8, 0x02DD, 0x02DB, 0x02C7,
+    };
+    // clang-format on
+
+    for (u8 ch : input) {
+        if (ch < 0x80) { // Superset of ASCII
+            on_code_point(ch);
+        } else {
+            on_code_point(translation_table[ch - 0x80]);
+        }
+    }
+}
+
 void TurkishDecoder::process(StringView input, Function<void(u32)> on_code_point)
 {
     auto convert_turkish_to_utf8 = [](u8 ch) -> u32 {
diff --git a/Userland/Libraries/LibTextCodec/Decoder.h b/Userland/Libraries/LibTextCodec/Decoder.h
index 6faf61fce5..02cdfba599 100644
--- a/Userland/Libraries/LibTextCodec/Decoder.h
+++ b/Userland/Libraries/LibTextCodec/Decoder.h
@@ -69,6 +69,11 @@ public:
     virtual void process(StringView, Function<void(u32)> on_code_point) override;
 };
 
+class MacRomanDecoder final : public Decoder {
+public:
+    virtual void process(StringView, Function<void(u32)> on_code_point) override;
+};
+
 class TurkishDecoder final : public Decoder {
 public:
     virtual void process(StringView, Function<void(u32)> on_code_point) override;