dmaax/ladybird
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

LibWeb: Implement chardetng-based encoding detection for HTML parsing

Browse source
This commit is contained in:
Martin Chrástek 2026-05-23 11:00:51 +02:00 committed by Shannon Booth
parent a404efa999
commit cd3c72dfda
101 changed files with 1077 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
Cargo.lock generated
View file

@ -139,6 +139,17 @@ version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "chardetng"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13de944a44b5064ee5d3a5ceccc49a41bfec50f2580e66f82e87703acdb88b53"
dependencies = [
"cfg-if",
"encoding_rs",
"memchr",
]
[[package]]
name = "clap"
version = "4.6.0"
@ -304,6 +315,15 @@ dependencies = [
"syn",
]
[[package]]
name = "encoding_rs"
version = "0.8.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
dependencies = [
"cfg-if",
]
[[package]]
name = "equivalent"
version = "1.0.2"
@ -597,6 +617,7 @@ name = "libweb_rust"
version = "0.1.0"
dependencies = [
"cbindgen",
"chardetng",
"libweb_html_tokenizer",
]

8
Libraries/LibWeb/CMakeLists.txt
View file

@ -1276,10 +1276,12 @@ if(NOT BUILD_SHARED_LIBS)
# POST_BUILD steps don't track inputs, so when libweb_rust.a changes
# ninja leaves liblagom-web.a alone and the merged archive ends up with
# stale Rust objects. Force the C++ FFI bridge file to depend on the
# Rust archive: when it changes, RustTokenizer.cpp recompiles, LibWeb
# re-archives, and POST_BUILD re-merges the fresh Rust objects.
# stale Rust objects. Force both FFI bridge files to depend on the
# Rust archive: when it changes, they recompile, LibWeb re-archives, and
# POST_BUILD re-merges the fresh Rust objects.
get_target_property(_libweb_rust_lib libweb_rust IMPORTED_LOCATION)
set_property(SOURCE CSS/Parser/RustTokenizer.cpp APPEND PROPERTY OBJECT_DEPENDS ${_libweb_rust_lib})
set_property(SOURCE HTML/Parser/HTMLEncodingDetection.cpp APPEND PROPERTY OBJECT_DEPENDS ${_libweb_rust_lib})
endif()
if (HAS_FONTCONFIG)

3
Libraries/LibWeb/HTML/FormAssociatedElement.cpp
View file

@ -321,8 +321,7 @@ String FormAssociatedElement::form_action() const
return html_element.document().url_string();
}
auto document_base_url = html_element.document().base_url();
if (auto maybe_url = document_base_url.complete_url(form_action_attribute.value()); maybe_url.has_value())
if (auto maybe_url = html_element.document().encoding_parse_url(form_action_attribute.value()); maybe_url.has_value())
return maybe_url->to_string();
return {};
}

5
Libraries/LibWeb/HTML/HTMLBaseElement.cpp
View file

@ -7,6 +7,7 @@
#include <LibWeb/Bindings/HTMLBaseElement.h>
#include <LibWeb/ContentSecurityPolicy/BlockingAlgorithms.h>
#include <LibWeb/DOM/Document.h>
#include <LibWeb/DOMURL/DOMURL.h>
#include <LibWeb/HTML/HTMLBaseElement.h>
namespace Web::HTML {
@ -113,8 +114,8 @@ String HTMLBaseElement::href() const
auto url = attribute(AttributeNames::href).value_or(String {});
// 3. Let urlRecord be the result of parsing url with document's fallback base URL, and document's character encoding. (Thus, the base element isn't affected by other base elements or itself.)
// FIXME: Pass in document's character encoding.
auto url_record = document.fallback_base_url().complete_url(url);
auto encoding = document.encoding_or_default();
auto url_record = DOMURL::parse(url, document.fallback_base_url(), encoding.bytes_as_string_view());
// 4. If urlRecord is failure, return url.
if (!url_record.has_value())

2
Libraries/LibWeb/HTML/HTMLFormElement.cpp
View file

@ -680,7 +680,7 @@ String HTMLFormElement::action() const
return document().url_string();
}
if (auto maybe_url = document().base_url().complete_url(form_action_attribute.value()); maybe_url.has_value())
if (auto maybe_url = document().encoding_parse_url(form_action_attribute.value()); maybe_url.has_value())
return maybe_url->to_string();
return {};
}

47
Libraries/LibWeb/HTML/Parser/HTMLEncodingDetection.cpp
View file

@ -8,12 +8,13 @@
#include <AK/CharacterTypes.h>
#include <AK/GenericLexer.h>
#include <AK/StringView.h>
#include <AK/Utf8View.h>
#include <LibTextCodec/Decoder.h>
#include <LibURL/URL.h>
#include <LibWeb/DOM/Attr.h>
#include <LibWeb/DOM/Document.h>
#include <LibWeb/Fetch/Infrastructure/HTTP/MIME.h>
#include <LibWeb/HTML/Parser/HTMLEncodingDetection.h>
#include <LibWeb/HTML/Parser/RustFFI.h>
#include <LibWeb/Infra/CharacterTypes.h>
namespace Web::HTML {
@ -459,6 +460,23 @@ Optional<ByteString> run_bom_sniff(ReadonlyBytes input)
return {};
}
ByteString extract_tld_hint(URL::URL const& url)
{
// Extract the rightmost DNS label from the URL's host as a TLD hint for chardetng.
// chardetng uses this to improve detection accuracy for country-code TLDs (.jp, .ru, .cn, …).
// Skip IP addresses — only domain names have meaningful TLDs.
auto const& maybe_host = url.host();
if (!maybe_host.has_value() || !maybe_host->is_domain())
return {};
auto host_string = maybe_host->serialize();
StringView host_view = host_string;
auto last_dot = host_view.find_last('.');
StringView tld_label = last_dot.has_value()
? host_view.substring_view(*last_dot + 1)
: host_view;
return tld_label.is_empty() ? ByteString {} : ByteString { tld_label };
}
// https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
ByteString run_encoding_sniffing_algorithm(DOM::Document& document, ReadonlyBytes input, Optional<MimeSniff::MimeType> maybe_mime_type)
{
@ -499,12 +517,27 @@ ByteString run_encoding_sniffing_algorithm(DOM::Document& document, ReadonlyByte
// 7. Otherwise, if the user agent has information on the likely encoding for this page, e.g. based on the encoding of the page when it was last visited, then return
// that encoding, with the confidence tentative.
// 8. FIXME: The user agent may attempt to autodetect the character encoding from applying frequency analysis or other algorithms to the data stream. Such algorithms
// may use information about the resource other than the resource's contents, including the address of the resource. If autodetection succeeds in determining a
// character encoding, and that encoding is a supported encoding, then return that encoding, with the confidence tentative. [UNIVCHARDET]
if (!Utf8View(StringView(input)).validate()) {
// FIXME: As soon as Locale is supported, this should sometimes return a different encoding based on the locale.
return "windows-1252";
// 8. The user agent may attempt to autodetect the character encoding from applying frequency analysis
// or other algorithms to the data stream. Such algorithms may use information about the resource
// other than the resource's contents, including the address of the resource.
// If autodetection succeeds in determining a character encoding, and that encoding is a supported encoding,
// then return that encoding, with the confidence tentative. [UNIVCHARDET]
auto tld_hint = extract_tld_hint(document.url());
u8 const* tld_data = tld_hint.is_empty() ? nullptr : reinterpret_cast<u8 const*>(tld_hint.characters());
size_t tld_size = tld_hint.length();
u8 const* encoding_name_ptr = nullptr;
size_t encoding_name_len = 0;
if (Parser::rust_detect_encoding(
input.data(), input.size(),
tld_data, tld_size,
&encoding_name_ptr, &encoding_name_len)) {
auto detected = StringView { reinterpret_cast<char const*>(encoding_name_ptr), encoding_name_len };
auto standardized = TextCodec::get_standardized_encoding(detected);
if (standardized.has_value())
return ByteString { standardized.value() };
}
// 9. Otherwise, return an implementation-defined or user-specified default character encoding, with the confidence tentative.

10
Libraries/LibWeb/HTML/Parser/HTMLEncodingDetection.h
View file

@ -10,6 +10,7 @@
#include <AK/ByteString.h>
#include <AK/Optional.h>
#include <LibGC/Ptr.h>
#include <LibURL/URL.h>
#include <LibWeb/Forward.h>
#include <LibWeb/MimeSniff/MimeType.h>
@ -19,6 +20,13 @@ Optional<StringView> extract_character_encoding_from_meta_element(ByteString con
GC::Ptr<DOM::Attr> prescan_get_attribute(DOM::Document&, ReadonlyBytes input, size_t& position);
Optional<ByteString> run_prescan_byte_stream_algorithm(DOM::Document&, ReadonlyBytes input);
Optional<ByteString> run_bom_sniff(ReadonlyBytes input);
ByteString run_encoding_sniffing_algorithm(DOM::Document&, ReadonlyBytes input, Optional<MimeSniff::MimeType> maybe_mime_type = {});
// Extracts the rightmost DNS label from a URL's host as a TLD hint for chardetng.
// Returns an empty string if the host is absent or is an IP address. chardetng treats
// an absent/empty TLD as equivalent to ".com".
ByteString extract_tld_hint(URL::URL const&);
ByteString run_encoding_sniffing_algorithm(DOM::Document&, ReadonlyBytes input,
Optional<MimeSniff::MimeType> maybe_mime_type = {});
}

1
Libraries/LibWeb/Rust/Cargo.toml
View file

@ -10,6 +10,7 @@ crate-type = ["staticlib"]
# python3 Meta/CMake/flatpak/generate-cargo-sources.py
[dependencies]
libweb_html_tokenizer = { path = "../HTML/Parser/Rust" }
chardetng = "1.0.0"
[build-dependencies]
cbindgen = "0.29"

24
Libraries/LibWeb/Rust/build.rs
View file

@ -24,7 +24,7 @@ fn main() -> Result<(), Box<dyn Error>> {
let base_config = cbindgen::Config::from_file(manifest_dir.join("cbindgen.toml"))?;
// CSS tokenizer header — namespace Web::CSS::Parser::FFI, CSS types only.
let mut css_config = base_config;
let mut css_config = base_config.clone();
css_config.namespaces = Some(vec![
"Web".to_string(),
"CSS".to_string(),
@ -51,5 +51,27 @@ fn main() -> Result<(), Box<dyn Error>> {
},
);
// Encoding-detection header — namespace Web::HTML::Parser, rust_detect_encoding only.
let mut html_config = base_config;
html_config.namespaces = Some(vec!["Web".to_string(), "HTML".to_string(), "Parser".to_string()]);
html_config.export.include = vec!["rust_detect_encoding".to_string()];
cbindgen::generate_with_config(&manifest_dir, html_config).map_or_else(
|error| match error {
cbindgen::Error::ParseSyntaxError { .. } => {}
other => panic!("{other:?}"),
},
|bindings| {
let html_header_dir = out_dir.join("HTML").join("Parser");
std::fs::create_dir_all(&html_header_dir).unwrap();
bindings.write_to_file(html_header_dir.join("RustFFI.h"));
if ffi_out_dir != out_dir {
let dest = ffi_out_dir.join("HTML").join("Parser");
std::fs::create_dir_all(&dest).unwrap();
bindings.write_to_file(dest.join("RustFFI.h"));
}
},
);
Ok(())
}

73
Libraries/LibWeb/Rust/src/encoding_detection.rs Normal file
View file

@ -0,0 +1,73 @@
/*
* Copyright (c) 2026-present, the Ladybird developers.
*
* SPDX-License-Identifier: BSD-2-Clause
*/
use chardetng::{EncodingDetector, Iso2022JpDetection, Utf8Detection};
/// Attempts to detect the character encoding of a byte stream using frequency analysis.
///
/// This implements step 8 of the WHATWG encoding sniffing algorithm:
/// https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
///
/// # Safety
/// - `input` and `input_len` must describe a valid byte slice (or `input` may be null if
/// `input_len` is 0)
/// - `tld` if non-null, must describe a valid byte slice of `tld_len` bytes containing the
/// rightmost DNS label of the resource's host, with no dots, no uppercase, and only ASCII
/// characters — these constraints are required by chardetng and must be validated by the caller
/// - `out_encoding_name` and `out_encoding_name_len` must be non-null writable pointers
///
/// Returns `true` if an encoding was detected (always, unless the input pointer is invalid).
/// When `true` is returned, `*out_encoding_name` is set to a pointer into a static ASCII
/// string naming the detected encoding (e.g. `"windows-1252"`, `"Shift_JIS"`), and
/// `*out_encoding_name_len` is set to its byte length. The pointer is valid for the lifetime
/// of the process. When `false` is returned (only on null-pointer error), the output pointers
/// are left unmodified.
#[unsafe(no_mangle)]
pub unsafe extern "C" fn rust_detect_encoding(
input: *const u8,
input_len: usize,
tld: *const u8,
tld_len: usize,
out_encoding_name: *mut *const u8,
out_encoding_name_len: *mut usize,
) -> bool {
unsafe {
crate::abort_on_panic(|| {
let Some(input_slice) = crate::bytes_from_raw(input, input_len) else {
return false;
};
let tld_slice = if tld.is_null() || tld_len == 0 {
None
} else {
Some(std::slice::from_raw_parts(tld, tld_len))
};
// Web browsers must use `Iso2022JpDetection::Deny` and `Utf8Detection::Deny` to
// prevent charset confusion attacks. See the chardetng documentation for details.
// Japanese pages using ISO-2022-JP will have declared it in a <meta> tag, which
// is detected in step 5 (prescan) before this step is reached.
// We always call `guess()` even for pure-ASCII input because chardetng still
// tracks ESC sequences (ISO-2022-JP uses 7-bit escapes) and returns the
// correct locale-based fallback (windows-1252 for generic TLD) with
// `Utf8Detection::Deny` when no distinctive non-ASCII encoding evidence is found.
let mut detector = EncodingDetector::new(Iso2022JpDetection::Deny);
// Pass last=false because the caller may only be providing a sniff-bytes prefix
// of a longer stream. chardetng docs: "If you want to perform detection on just
// the prefix of a longer stream, do not pass last=true."
detector.feed(input_slice, false);
// `Utf8Detection::Deny`: chardetng never returns UTF-8 here; valid-UTF-8
// content (including pure ASCII) gets the TLD-based default (windows-1252
// for generic), while content in a non-UTF-8 encoding gets that encoding.
let encoding = detector.guess(tld_slice, Utf8Detection::Deny);
let name = encoding.name().as_bytes();
*out_encoding_name = name.as_ptr();
*out_encoding_name_len = name.len();
true
})
}
}

1
Libraries/LibWeb/Rust/src/lib.rs
View file

@ -8,6 +8,7 @@
mod rust_allocator;
mod css_tokenizer;
mod encoding_detection;
pub use libweb_html_tokenizer as html_tokenizer;

16
Meta/CMake/flatpak/cargo-sources.json
View file

@ -110,6 +110,13 @@
"sha256": "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801",
"dest": "cargo/vendor/cfg-if-1.0.4"
},
{
"type": "archive",
"archive-type": "tar-gzip",
"url": "https://static.crates.io/crates/chardetng/chardetng-1.0.0.crate",
"sha256": "13de944a44b5064ee5d3a5ceccc49a41bfec50f2580e66f82e87703acdb88b53",
"dest": "cargo/vendor/chardetng-1.0.0"
},
{
"type": "archive",
"archive-type": "tar-gzip",
@ -229,6 +236,13 @@
"sha256": "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0",
"dest": "cargo/vendor/displaydoc-0.2.5"
},
{
"type": "archive",
"archive-type": "tar-gzip",
"url": "https://static.crates.io/crates/encoding_rs/encoding_rs-0.8.35.crate",
"sha256": "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3",
"dest": "cargo/vendor/encoding_rs-0.8.35"
},
{
"type": "archive",
"archive-type": "tar-gzip",
@ -898,6 +912,7 @@
"echo '{\"files\": {}, \"package\": \"5abbd6eeda6885048d357edc66748eea6e0268e3dd11f326fff5bd248d779c26\"}' > cargo/vendor/calendrical_calculations-0.2.4/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"befbfd072a8e81c02f8c507aefce431fe5e7d051f83d48a23ffc9b9fe5a11799\"}' > cargo/vendor/cbindgen-0.29.2/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801\"}' > cargo/vendor/cfg-if-1.0.4/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"13de944a44b5064ee5d3a5ceccc49a41bfec50f2580e66f82e87703acdb88b53\"}' > cargo/vendor/chardetng-1.0.0/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"b193af5b67834b676abd72466a96c1024e6a6ad978a1f484bd90b85c94041351\"}' > cargo/vendor/clap-4.6.0/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f\"}' > cargo/vendor/clap_builder-4.6.0/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9\"}' > cargo/vendor/clap_lex-1.1.0/.cargo-checksum.json",
@ -915,6 +930,7 @@
"echo '{\"files\": {}, \"package\": \"4d55612bebcf16ff7306c8a6f5bdb6d45662b8aa1ee058ecce8807ad87db719b\"}' > cargo/vendor/cranelift-module-0.116.1/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"b8dee82f3f1f2c4cba9177f1cc5e350fe98764379bcd29340caa7b01f85076c7\"}' > cargo/vendor/cranelift-native-0.116.1/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0\"}' > cargo/vendor/displaydoc-0.2.5/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3\"}' > cargo/vendor/encoding_rs-0.8.35/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f\"}' > cargo/vendor/equivalent-1.0.2/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb\"}' > cargo/vendor/errno-0.3.14/.cargo-checksum.json",
"echo '{\"files\": {}, \"package\": \"2acce4a10f12dc2fb14a218589d4f1f62ef011b2d0cc4b3cb1bba8e94da14649\"}' > cargo/vendor/fallible-iterator-0.3.0/.cargo-checksum.json",

2
Tests/LibWeb/Text/expected/css/style-invalidation/has-concrete-structural-triggers.txt
View file

@ -1,4 +1,4 @@
PASS: inserted class argument invalidates descendant fanout | styleInvalidations=2, fullStyleInvalidations=0, elementStyleRecomputations=13, elementStyleNoopRecomputations=5, elementInheritedStyleRecomputations=0, elementInheritedStyleNoopRecomputations=0, hasAncestorWalkInvocations=1, hasInvalidationMetadataCandidates=1, hasMatchInvocations=2, hasResultCacheHits=0, hasResultCacheMisses=2
PASS: inserted class argument invalidates descendant fanout | styleInvalidations=2, fullStyleInvalidations=0, elementStyleRecomputations=14, elementStyleNoopRecomputations=5, elementInheritedStyleRecomputations=0, elementInheritedStyleNoopRecomputations=0, hasAncestorWalkInvocations=1, hasInvalidationMetadataCandidates=1, hasMatchInvocations=2, hasResultCacheHits=0, hasResultCacheMisses=2
PASS: removed class argument invalidates descendant fanout | styleInvalidations=2, fullStyleInvalidations=0, elementStyleRecomputations=3, elementStyleNoopRecomputations=2, elementInheritedStyleRecomputations=0, elementInheritedStyleNoopRecomputations=0, hasAncestorWalkInvocations=1, hasInvalidationMetadataCandidates=0, hasMatchInvocations=2, hasResultCacheHits=0, hasResultCacheMisses=2
PASS: inserted id argument invalidates descendant fanout | styleInvalidations=3, fullStyleInvalidations=0, elementStyleRecomputations=4, elementStyleNoopRecomputations=2, elementInheritedStyleRecomputations=0, elementInheritedStyleNoopRecomputations=0, hasAncestorWalkInvocations=1, hasInvalidationMetadataCandidates=1, hasMatchInvocations=2, hasResultCacheHits=0, hasResultCacheMisses=2
PASS: removed id argument invalidates descendant fanout | styleInvalidations=2, fullStyleInvalidations=0, elementStyleRecomputations=3, elementStyleNoopRecomputations=2, elementInheritedStyleRecomputations=0, elementInheritedStyleNoopRecomputations=0, hasAncestorWalkInvocations=1, hasInvalidationMetadataCandidates=0, hasMatchInvocations=2, hasResultCacheHits=0, hasResultCacheMisses=2

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ar-ISO-8859-6.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ar-windows-1256.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ca-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/el-ISO-8859-7.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/el-windows-1253.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/en-copyright-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/en-euro-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/en-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/es-maria-windows-1252.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/es-nuestra-senora-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/es-number-one-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/es-ordinal-windows-1252.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/fa-windows-1256.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/fi-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/he-ISO-8859-8.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/he-windows-1255.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/is-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/it-number-one-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/it-ordinal-windows-1252.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/it-roman-ordinal-windows-1252.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/it-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ja-EUC-JP.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ja-ISO-2022-JP.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ja-Shift_JIS.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ja-half-width.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ko-EUC-KR.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/lt-windows-1257.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/lv-windows-1257.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/nbsp-even-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/nbsp-odd-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/pl-ISO-8859-2.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/pl-windows-1250.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/pt-windows-1252.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ru-IBM866.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/ru-ISO-8859-5.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/th-windows-874.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/tr-windows-1254.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/uk-KOI8-U.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/uk-windows-1251.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/utf-8.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/vi-windows-1258.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/yi-windows-1255.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/zh-Big5.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

6
Tests/LibWeb/Text/expected/wpt-import/encoding-detection/zh-GBK.tentative.txt Normal file
View file

@ -0,0 +1,6 @@
Harness status: OK
Found 1 tests
1 Pass
Pass Check detection result

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ar-ISO-8859-6.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ar ISO-8859-6</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>çÐÇ çè ÇÎÊÈÇÑ ÊÑåêÒ ÇäÃÍÑá.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "ISO-8859-6", 'Expected ISO-8859-6');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ar-windows-1256.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ar windows-1256</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>åÐÇ åæ ÇÎÊÈÇÑ ÊÑãíÒ ÇáÃÍÑÝ.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1256", 'Expected windows-1256');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ca-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ca windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Es tracta d’una prova de codificació de caràcters.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

15
Tests/LibWeb/Text/input/wpt-import/encoding-detection/el-ISO-8859-7.tentative.html Normal file
View file

@ -0,0 +1,15 @@
<!doctype html>
<title>el ISO-8859-7</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ðñüêåéôáé ãéá äïêéìÞ êùäéêïðïßçóçò ÷áñáêôÞñùí: ¶ñçò
<!-- I needed to work capital alpha with tonos into the test somehow... --></p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "ISO-8859-7", 'Expected ISO-8859-7');
}, "Check detection result");
done();
};
</script>

15
Tests/LibWeb/Text/input/wpt-import/encoding-detection/el-windows-1253.tentative.html Normal file
View file

@ -0,0 +1,15 @@
<!doctype html>
<title>el windows-1253</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ðñüêåéôáé ãéá äïêéìÞ êùäéêïðïßçóçò ÷áñáêôÞñùí: ¢ñçò
<!-- I needed to work capital alpha with tonos into the test somehow... --></p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1253", 'Expected windows-1253');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/en-copyright-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>en windows-1252 copyright sign</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Copyright © 2021</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/en-euro-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>en windows-1252 euro sign</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>It costs €9.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/en-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>en windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>I’ve made an encoding test.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/es-maria-windows-1252.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>es windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Mª</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/es-nuestra-senora-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>es windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Nª Sª</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/es-number-one-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>es windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>n.º1</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/es-ordinal-windows-1252.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>es windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>42.º</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/fa-windows-1256.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>fa windows-1256</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ç&#1740;ä &#1740;˜ ÊÓÊ ÑãÒ<C3A3>ÐÇÑ&#1740; ˜ÇÑǘÊÑ ÇÓÊ.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1256", 'Expected windows-1256');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/fi-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>fi windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Tämä on merkkikoodaustesti.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/he-ISO-8859-8.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>he ISO-8859-8</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>.íéååú ãåãé÷ ïçáî åäæ</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "ISO-8859-8", 'Expected ISO-8859-8');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/he-windows-1255.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>he windows-1255</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>æäå îáçï ÷éãåã úååéí.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1255", 'Expected windows-1255');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/is-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>is windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Þetta er kóðunarpróf á staf. Fyrir sum tungumál sem nota latneska stafi þurfum við meira inntak til að taka ákvörðunina.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/it-number-one-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>fi windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Nº1</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/it-ordinal-windows-1252.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>it windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>42º</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/it-roman-ordinal-windows-1252.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>it windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>IIIª</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/it-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>it windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Questo è un test di codifica dei caratteri.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ja-EUC-JP.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ja EUC-JP</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>これは矢机悸赋です。</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "EUC-JP", 'Expected EUC-JP');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ja-ISO-2022-JP.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ja ISO-2022-JP</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>$B$3$l$OJ8;z<B83$G$9!#(B</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252 due to ISO-2022-JP no longer getting detected');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ja-Shift_JIS.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ja Shift_JIS</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>これは文字実験です。</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "Shift_JIS", 'Expected Shift_JIS');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ja-half-width.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ja Shift_JIS half-width katakana</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ê°ÄÞ³ª±Ê°ÄÞ³ª±Ê°ÄÞ³ª±Ê°ÄÞ³ª±Ê°ÄÞ³ª±</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "Shift_JIS", 'Expected Shift_JIS');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ko-EUC-KR.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ko EUC-KR</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>이것은 문자 인코딩 테스트입니다.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "EUC-KR", 'Expected EUC-KR');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/lt-windows-1257.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>lt windows-1257</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Tai simboliø kodavimo testas. Kai kurioms kalboms, naudojanèioms lotyniðkus raðmenis, mums reikia daugiau informacijos, kad galëtume priimti sprendimà.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1257", 'Expected windows-1257');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/lv-windows-1257.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>lv windows-1257</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ðis ir rakstzîmju kodçðanas tests. Daþâs valodâs, kurâs tiek izmantotas latîòu valodas burti, lçmuma pieòemðanai mums ir nepiecieðams vairâk ieguldîjuma.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1257", 'Expected windows-1257');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/nbsp-even-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>nbsp even windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>No-break    spaces</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/nbsp-odd-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>nbsp odd windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>No-break      spaces</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/pl-ISO-8859-2.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>pl ISO-8859-2</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>To jest test kodowania znaków. W przypadku niektórych jêzyków, które u¿ywaj± znaków ³aciñskich, potrzebujemy wiêcej danych, aby podj±æ decyzjê.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "ISO-8859-2", 'Expected ISO-8859-2');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/pl-windows-1250.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>pl windows-1250</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>To jest test kodowania znaków. W przypadku niektórych jêzyków, które u¿ywaj¹ znaków ³aciñskich, potrzebujemy wiêcej danych, aby podj¹æ decyzjê.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1250", 'Expected windows-1250');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/pt-windows-1252.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>pt windows-1252</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Este é um teste de codificação de caracteres.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1252", 'Expected windows-1252');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ru-IBM866.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ru IBM866</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p><EFBFBD>â® â¥áâ ª®¤¨à®¢ª¨ ᨬ¢®«®¢.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "IBM866", 'Expected IBM866');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/ru-ISO-8859-5.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>ru ISO-8859-5</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>ÍâÞ âÕáâ ÚÞÔØàÞÒÚØ áØÜÒÞÛÞÒ.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "ISO-8859-5", 'Expected ISO-8859-5');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/th-windows-874.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>th windows-874</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>¹Õè¤×Í¡Ò÷´Êͺ¡ÒÃà¢éÒÃËÑÊÍÑ¡¢ÃÐ</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-874", 'Expected windows-874');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/tr-windows-1254.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>tr windows-1254</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Bu bir karakter kodlama testidir. Latince karakterleri kullanan bazý dillerde karar vermek için daha fazla girdiye ihtiyacýmýz var.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1254", 'Expected windows-1254');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/uk-KOI8-U.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>uk KOI8-U</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>ãÅ ÔÅÓÔ ÎÁ ËÏÄÕ×ÁÎÎÑ ÓÉÍ×Ï̦×.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "KOI8-U", 'Expected KOI8-U');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/uk-windows-1251.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>uk windows-1251</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Öå òåñò íà êîäóâàííÿ ñèìâîë³â.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1251", 'Expected windows-1251');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/utf-8.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>UTF-8</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>これは文字実験です。</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_not_equals(document.characterSet.toUpperCase(), "UTF-8", 'Must not detect UTF-8');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/vi-windows-1258.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>vi windows-1258</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>Ðây laÌ môòt thýÒ nghiêòm maÞ hoìa kyì týò.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1258", 'Expected windows-1258');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/yi-windows-1255.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>yi windows-1255</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>ãàÈñ àéæ àÇ èòñè ôÏàÇø ÷àÈãéøåðâ ôåï ëàÇøàÇ÷èòø.</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "windows-1255", 'Expected windows-1255');
}, "Check detection result");
done();
};
</script>

14
Tests/LibWeb/Text/input/wpt-import/encoding-detection/zh-Big5.tentative.html Normal file
View file

@ -0,0 +1,14 @@
<!doctype html>
<title>zh Big5</title>
<script src=../resources/testharness.js></script>
<script src=../resources/testharnessreport.js></script>
<p>這是一個字符編碼測試。</p>
<script>
setup({explicit_done:true});
onload = function() {
test(function() {
assert_equals(document.characterSet, "Big5", 'Expected Big5');
}, "Check detection result");
done();
};
</script>

Some files were not shown because too many files have changed in this diff Show more