LibTextCodec: Remove unused PDFDocEncoding
PDFDocEncoding has no remaining users left. Remove the decoder and label plumbing. Retarget the lazy source-code decoding regression test to Windows-1252 so it still covers non-UTF source decoding.
This commit is contained in:
Shannon Booth
Andreas Kling
parent
784ca98041
commit
c982385ffe
3 changed files with 5 additions and 69 deletions
|
|
@ -26,7 +26,6 @@ Latin1Decoder s_latin1_decoder;
|
|||
UTF8Decoder s_utf8_decoder;
|
||||
UTF16BEDecoder s_utf16be_decoder;
|
||||
UTF16LEDecoder s_utf16le_decoder;
|
||||
PDFDocEncodingDecoder s_pdf_doc_encoding_decoder;
|
||||
XUserDefinedDecoder s_x_user_defined_decoder;
|
||||
GB18030Decoder s_gb18030_decoder;
|
||||
Big5Decoder s_big5_decoder;
|
||||
|
|
@ -130,8 +129,6 @@ Optional<Decoder&> decoder_for_exact_name(StringView encoding)
|
|||
return s_koi8u_decoder;
|
||||
if (encoding.equals_ignoring_ascii_case("macintosh"sv))
|
||||
return s_mac_roman_decoder;
|
||||
if (encoding.equals_ignoring_ascii_case("PDFDocEncoding"sv))
|
||||
return s_pdf_doc_encoding_decoder;
|
||||
if (encoding.equals_ignoring_ascii_case("replacement"sv))
|
||||
return s_replacement_decoder;
|
||||
if (encoding.equals_ignoring_ascii_case("shift_jis"sv))
|
||||
|
|
@ -206,8 +203,6 @@ Optional<StringView> get_standardized_encoding(StringView encoding)
|
|||
return "KOI8-U"sv;
|
||||
if (encoding.is_one_of_ignoring_ascii_case("csmacintosh"sv, "mac"sv, "macintosh"sv, "x-mac-roman"sv))
|
||||
return "macintosh"sv;
|
||||
if (encoding.is_one_of_ignoring_ascii_case("pdfdocencoding"sv))
|
||||
return "PDFDocEncoding"sv;
|
||||
if (encoding.is_one_of_ignoring_ascii_case("dos-874"sv, "iso-8859-11"sv, "iso8859-11"sv, "iso885911"sv, "tis-620"sv, "windows-874"sv))
|
||||
return "windows-874"sv;
|
||||
if (encoding.is_one_of_ignoring_ascii_case("cp1250"sv, "windows-1250"sv, "x-cp1250"sv))
|
||||
|
|
@ -1039,58 +1034,6 @@ ErrorOr<size_t> Latin1Decoder::length_in_utf16_code_units(StringView input)
|
|||
return input.length();
|
||||
}
|
||||
|
||||
ErrorOr<void> PDFDocEncodingDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
|
||||
{
|
||||
// PDF 1.7 spec, Appendix D.2 "PDFDocEncoding Character Set"
|
||||
// Character codes 0-8, 11-12, 14-23, 127, 159, 173 are not defined per spec.
|
||||
// clang-format off
|
||||
static constexpr Array<u32, 256> translation_table = {
|
||||
0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
|
||||
0x0008, 0x0009, 0x000A, 0x000B, 0x000C, 0x000D, 0x000E, 0x000F,
|
||||
0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0017, 0x0017,
|
||||
0x02D8, 0x02C7, 0x02C6, 0x02D9, 0x02DD, 0x02DB, 0x02DA, 0x02DC,
|
||||
0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
|
||||
0x0028, 0x0029, 0x002A, 0x002B, 0x002C, 0x002D, 0x002E, 0x002F,
|
||||
0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
|
||||
0x0038, 0x0039, 0x003A, 0x003B, 0x003C, 0x003D, 0x003E, 0x003F,
|
||||
0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
|
||||
0x0048, 0x0049, 0x004A, 0x004B, 0x004C, 0x004D, 0x004E, 0x004F,
|
||||
0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
|
||||
0x0058, 0x0059, 0x005A, 0x005B, 0x005C, 0x005D, 0x005E, 0x005F,
|
||||
0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
|
||||
0x0068, 0x0069, 0x006A, 0x006B, 0x006C, 0x006D, 0x006E, 0x006F,
|
||||
0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
|
||||
0x0078, 0x0079, 0x007A, 0x007B, 0x007C, 0x007D, 0x007E, 0xFFFC,
|
||||
0x2022, 0x2020, 0x2021, 0x2026, 0x2014, 0x2013, 0x0192, 0x2044,
|
||||
0x2039, 0x203A, 0x2212, 0x2030, 0x201E, 0x201C, 0x201D, 0x2018,
|
||||
0x2019, 0x201A, 0x2122, 0xFB01, 0xFB02, 0x0141, 0x0152, 0x0160,
|
||||
0x0178, 0x017D, 0x0131, 0x0142, 0x0153, 0x0161, 0x017E, 0xFFFC,
|
||||
0x20AC, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
|
||||
0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0xFFFC, 0x00AE, 0x00AF,
|
||||
0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
|
||||
0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
|
||||
0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
||||
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
|
||||
0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
|
||||
0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
|
||||
0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
|
||||
0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
|
||||
0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
|
||||
0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF,
|
||||
};
|
||||
// clang-format on
|
||||
|
||||
for (u8 ch : input)
|
||||
TRY(on_code_point(translation_table[ch]));
|
||||
|
||||
return {};
|
||||
}
|
||||
|
||||
ErrorOr<size_t> PDFDocEncodingDecoder::length_in_utf16_code_units(StringView input)
|
||||
{
|
||||
return input.length();
|
||||
}
|
||||
|
||||
// https://encoding.spec.whatwg.org/#x-user-defined-decoder
|
||||
ErrorOr<void> XUserDefinedDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -87,13 +87,6 @@ public:
|
|||
virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
|
||||
};
|
||||
|
||||
class TEXTCODEC_API PDFDocEncodingDecoder final : public Decoder {
|
||||
public:
|
||||
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
|
||||
virtual bool validate(StringView) override { return true; }
|
||||
virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
|
||||
};
|
||||
|
||||
class TEXTCODEC_API XUserDefinedDecoder final : public Decoder {
|
||||
public:
|
||||
virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
|
||||
|
|
|
|||
|
|
@ -75,14 +75,14 @@ TEST_CASE(lazy_source_code_decoding_replaces_single_trailing_utf16_byte)
|
|||
EXPECT_EQ(source_code->source_text_from_offsets(0, 1).to_utf8(), "\xef\xbf\xbd"sv);
|
||||
}
|
||||
|
||||
TEST_CASE(lazy_source_code_decoding_uses_pdfdocencoding_mapping)
|
||||
TEST_CASE(lazy_source_code_decoding_uses_windows1252_mapping)
|
||||
{
|
||||
auto source_data = Vector<u8> { 0x18, 'A' };
|
||||
auto source_data = Vector<u8> { 0x80, 'A' };
|
||||
auto source_bytes = TRY_OR_FAIL(Core::ImmutableBytes::copy(source_data.span()));
|
||||
auto source_code = JS::SourceCode::create("test.js"_string, 2, "PDFDocEncoding"_string, move(source_bytes));
|
||||
auto source_code = JS::SourceCode::create("test.js"_string, 2, "windows-1252"_string, move(source_bytes));
|
||||
|
||||
EXPECT_EQ(source_code->source_text_from_offsets(0, 1).to_utf8(), "\xcb\x98"sv);
|
||||
EXPECT_EQ(source_code->code().to_utf8(), "\xcb\x98"
|
||||
EXPECT_EQ(source_code->source_text_from_offsets(0, 1).to_utf8(), "\xe2\x82\xac"sv);
|
||||
EXPECT_EQ(source_code->code().to_utf8(), "\xe2\x82\xac"
|
||||
"A"sv);
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue