Fuzzers: Use a single fuzzer to test all LibTextCodec encodings

This commit replaces the 5 fuzzers that previously tested LibTextCodec
with a single fuzzer. We now rely on the fuzzer to generate the
encoding and separate it from the encoded data with a magic separator.
This increases the overall coverage of LibTextCodec and eliminates the
possibility of the same error being generated by multiple fuzzers.

Meta/Lagom/Fuzzers/FuzzCyrillicDecoder.cpp

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2021, the SerenityOS developers.
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <LibTextCodec/Decoder.h>
-#include <stddef.h>
-#include <stdint.h>
-
-extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
-{
-    AK::set_debug_enabled(false);
-    auto decoder = TextCodec::decoder_for("windows-1251"sv);
-    VERIFY(decoder.has_value());
-    (void)decoder->to_utf8({ data, size });
-    return 0;
-}

Meta/Lagom/Fuzzers/FuzzHebrewDecoder.cpp

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2021, the SerenityOS developers.
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <LibTextCodec/Decoder.h>
-#include <stddef.h>
-#include <stdint.h>
-
-extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
-{
-    AK::set_debug_enabled(false);
-    auto decoder = TextCodec::decoder_for("windows-1255"sv);
-    VERIFY(decoder.has_value());
-    (void)decoder->to_utf8({ data, size });
-    return 0;
-}

Meta/Lagom/Fuzzers/FuzzLatin1Decoder.cpp

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2021, the SerenityOS developers.
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <LibTextCodec/Decoder.h>
-#include <stddef.h>
-#include <stdint.h>
-
-extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
-{
-    AK::set_debug_enabled(false);
-    auto decoder = TextCodec::decoder_for("windows-1252"sv);
-    VERIFY(decoder.has_value());
-    (void)decoder->to_utf8({ data, size });
-    return 0;
-}

Meta/Lagom/Fuzzers/FuzzLatin2Decoder.cpp

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2021, the SerenityOS developers.
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <LibTextCodec/Decoder.h>
-#include <stddef.h>
-#include <stdint.h>
-
-extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
-{
-    AK::set_debug_enabled(false);
-    auto decoder = TextCodec::decoder_for("iso-8859-2"sv);
-    VERIFY(decoder.has_value());
-    (void)decoder->to_utf8({ data, size });
-    return 0;
-}

Meta/Lagom/Fuzzers/FuzzTextDecoder.cpp

@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2021-2023, the SerenityOS developers.
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <LibTextCodec/Decoder.h>
+#include <stddef.h>
+#include <stdint.h>
+
+extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
+{
+    AK::set_debug_enabled(false);
+
+    static constexpr StringView MAGIC_SEPARATOR = "|DATA|"sv;
+    StringView data_string_view { data, size };
+    auto separator_index = data_string_view.find(MAGIC_SEPARATOR);
+    if (!separator_index.has_value())
+        return 0;
+
+    auto encoding = data_string_view.substring_view(0, separator_index.value());
+    auto encoded_data = data_string_view.substring_view(separator_index.value() + MAGIC_SEPARATOR.length());
+    auto decoder = TextCodec::decoder_for(encoding);
+    if (!decoder.has_value())
+        return 0;
+
+    (void)decoder->to_utf8(encoded_data);
+    return 0;
+}

Meta/Lagom/Fuzzers/FuzzTextDecoder.dict

@@ -0,0 +1,15 @@
+magic_separator="|DATA|"
+
+# encodings
+cyrillic_encoding="windows-1251"
+hebrew_encoding="windows-1255"
+koi8r_encoding="koi8-r"
+latin1_encoding="windows-1252"
+latin2_encoding="iso-8859-2"
+latin9_encoding="iso-8859-15"
+mac_roman_encoding="macintosh"
+turkish_encoding="windows-1254"
+user_defined_encoding="x-user-defined"
+utf16be_encoding="utf-16be"
+utf16le_encoding="utf-16le"
+utf8_encoding="utf-8"

Meta/Lagom/Fuzzers/FuzzUTF16BEDecoder.cpp

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2021, the SerenityOS developers.
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <LibTextCodec/Decoder.h>
-#include <stddef.h>
-#include <stdint.h>
-
-extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
-{
-    AK::set_debug_enabled(false);
-    auto decoder = TextCodec::decoder_for("utf-16be"sv);
-    VERIFY(decoder.has_value());
-    (void)decoder->to_utf8({ data, size });
-    return 0;
-}

Meta/Lagom/Fuzzers/fuzzers.cmake

@@ -3,7 +3,6 @@ set(FUZZER_TARGETS
     BLAKE2b
     BMPLoader
     Brotli
-    CyrillicDecoder
     DDSLoader
     DNSPacket
     DeflateCompression
@@ -14,7 +13,6 @@ set(FUZZER_TARGETS
     GIFLoader
     GzipCompression
     GzipDecompression
-    HebrewDecoder
     HttpRequest
     ICCProfile
     ICOLoader
@@ -23,8 +21,6 @@ set(FUZZER_TARGETS
     JPEGLoader
     Js
     JsonParser
-    Latin1Decoder
-    Latin2Decoder
     LzmaDecompression
     LzmaRoundtrip
     Markdown
@@ -53,12 +49,12 @@ set(FUZZER_TARGETS
     ShellPosix
     SQLParser
     Tar
+    TextDecoder
     TGALoader
     TIFFLoader
     TTF
     TinyVGLoader
     URL
-    UTF16BEDecoder
     VP9Decoder
     WasmParser
     WAVLoader
@@ -79,7 +75,6 @@ set(FUZZER_DEPENDENCIES_BLAKE2b LibCrypto)
 set(FUZZER_DEPENDENCIES_BMPLoader LibGfx)
 set(FUZZER_DEPENDENCIES_Brotli LibCompress)
 set(FUZZER_DEPENDENCIES_CSSParser LibWeb)
-set(FUZZER_DEPENDENCIES_CyrillicDecoder LibTextCodec)
 set(FUZZER_DEPENDENCIES_DDSLoader LibGfx)
 set(FUZZER_DEPENDENCIES_DNSPacket LibDNS)
 set(FUZZER_DEPENDENCIES_DeflateCompression LibCompress)
@@ -90,7 +85,6 @@ set(FUZZER_DEPENDENCIES_Gemini LibGemini)
 set(FUZZER_DEPENDENCIES_GIFLoader LibGfx)
 set(FUZZER_DEPENDENCIES_GzipCompression LibCompress)
 set(FUZZER_DEPENDENCIES_GzipDecompression LibCompress)
-set(FUZZER_DEPENDENCIES_HebrewDecoder LibTextCodec)
 set(FUZZER_DEPENDENCIES_HttpRequest LibHTTP)
 set(FUZZER_DEPENDENCIES_ICCProfile LibGfx)
 set(FUZZER_DEPENDENCIES_ICOLoader LibGfx)
@@ -98,8 +92,6 @@ set(FUZZER_DEPENDENCIES_ILBMLoader LibGfx)
 set(FUZZER_DEPENDENCIES_IMAPParser LibIMAP)
 set(FUZZER_DEPENDENCIES_JPEGLoader LibGfx)
 set(FUZZER_DEPENDENCIES_Js LibJS)
-set(FUZZER_DEPENDENCIES_Latin1Decoder LibTextCodec)
-set(FUZZER_DEPENDENCIES_Latin2Decoder LibTextCodec)
 set(FUZZER_DEPENDENCIES_LzmaDecompression LibArchive LibCompress)
 set(FUZZER_DEPENDENCIES_LzmaRoundtrip LibCompress)
 set(FUZZER_DEPENDENCIES_Markdown LibMarkdown)
@@ -128,11 +120,11 @@ set(FUZZER_DEPENDENCIES_Shell LibShell)
 set(FUZZER_DEPENDENCIES_ShellPosix LibShell)
 set(FUZZER_DEPENDENCIES_SQLParser LibSQL)
 set(FUZZER_DEPENDENCIES_Tar LibArchive)
+set(FUZZER_DEPENDENCIES_TextDecoder LibTextCodec)
 set(FUZZER_DEPENDENCIES_TGALoader LibGfx)
 set(FUZZER_DEPENDENCIES_TIFFLoader LibGfx)
 set(FUZZER_DEPENDENCIES_TTF LibGfx)
 set(FUZZER_DEPENDENCIES_TinyVGLoader LibGfx)
-set(FUZZER_DEPENDENCIES_UTF16BEDecoder LibTextCodec)
 set(FUZZER_DEPENDENCIES_VP9Decoder LibVideo)
 set(FUZZER_DEPENDENCIES_WasmParser LibWasm)
 set(FUZZER_DEPENDENCIES_WAVLoader LibAudio)

Userland/Utilities/test-fuzz.cpp

@@ -17,7 +17,6 @@
     T(BMPLoader)             \
     T(Brotli)                \
     T(CSSParser)             \
-    T(CyrillicDecoder)       \
     T(DDSLoader)             \
     T(DNSPacket)             \
     T(DeflateCompression)    \
@@ -28,7 +27,6 @@
     T(GIFLoader)             \
     T(GzipCompression)       \
     T(GzipDecompression)     \
-    T(HebrewDecoder)         \
     T(HttpRequest)           \
     T(ICCProfile)            \
     T(ICOLoader)             \
@@ -37,8 +35,6 @@
     T(JPEGLoader)            \
     T(Js)                    \
     T(JsonParser)            \
-    T(Latin1Decoder)         \
-    T(Latin2Decoder)         \
     T(LzmaDecompression)     \
     T(LzmaRoundtrip)         \
     T(Markdown)              \
@@ -67,12 +63,12 @@
     T(ShellPosix)            \
     T(SQLParser)             \
     T(Tar)                   \
+    T(TextDecoder)           \
     T(TGALoader)             \
     T(TIFFLoader)            \
     T(TTF)                   \
     T(TinyVGLoader)          \
     T(URL)                   \
-    T(UTF16BEDecoder)        \
     T(VP9Decoder)            \
     T(WasmParser)            \
     T(WAVLoader)             \