beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 07:30:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

AK: Improve the parsing of data urls

Browse source 
Improve the parsing of data urls in URLParser to bring it more up-to-
spec. At the moment, we cannot parse the components of the MIME type
since it is represented as a string, but the spec requires it to be
parsed as a "MIME type record".
This commit is contained in:
TheFightingCatfish 2021-08-05 00:29:06 +08:00 committed by Andreas Kling
parent f5c3225286
commit 4e8e1b7b3a
Notes: sideshowbarker 2024-07-18 07:25:04 +09:00 
Author: https://github.com/SeekingBlues
Commit: https://github.com/SerenityOS/serenity/commit/4e8e1b7b3a2
Pull-request: https://github.com/SerenityOS/serenity/pull/9207
2 changed files with 55 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
AK/URLParser.cpp
View file

@ -116,7 +116,7 @@ constexpr bool is_double_dot_path_segment(StringView const& input)
}
// https://fetch.spec.whatwg.org/#data-urls
// FIXME: This only loosely follow the spec, as we use the same class for "regular" and data URLs, unlike the spec.
// FIXME: This only loosely follows the spec, as we use the same class for "regular" and data URLs, unlike the spec.
Optional<URL> URLParser::parse_data_url(StringView const& raw_input)
{
dbgln_if(URL_PARSER_DEBUG, "URLParser::parse_data_url: Parsing '{}'.", raw_input);
@ -125,24 +125,28 @@ Optional<URL> URLParser::parse_data_url(StringView const& raw_input)
auto comma_offset = input.find(',');
if (!comma_offset.has_value())
return {};
auto mime_type = input.substring_view(0, comma_offset.value());
// FIXME: Strip leading and trailing ASCII whitespace from mimeType
auto mime_type = StringUtils::trim(input.substring_view(0, comma_offset.value()), "\t\n\f\r ", TrimMode::Both);
auto encoded_body = input.substring_view(comma_offset.value() + 1);
auto body = URL::percent_decode(encoded_body);
bool is_base_64_encoded = false;
if (mime_type.ends_with(";base64", CaseSensitivity::CaseInsensitive)) {
is_base_64_encoded = true;
mime_type = mime_type.substring_view(0, mime_type.length() - 7);
bool is_base64_encoded = false;
if (mime_type.ends_with("base64", CaseSensitivity::CaseInsensitive)) {
auto substring_view = mime_type.substring_view(0, mime_type.length() - 6);
auto trimmed_substring_view = StringUtils::trim(substring_view, " ", TrimMode::Right);
if (trimmed_substring_view.ends_with(';')) {
is_base64_encoded = true;
mime_type = trimmed_substring_view.substring_view(0, trimmed_substring_view.length() - 1);
}
}
if (mime_type.starts_with(";")) {
StringBuilder builder;
StringBuilder builder;
if (mime_type.starts_with(";") || mime_type.is_empty()) {
builder.append("text/plain");
builder.append(mime_type);
mime_type = builder.to_string();
mime_type = builder.string_view();
}
URL url { mime_type, move(body), is_base_64_encoded };
// FIXME: Parse the MIME type's components according to https://mimesniff.spec.whatwg.org/#parse-a-mime-type
URL url { StringUtils::trim(mime_type, "\n\r\t ", TrimMode::Both), move(body), is_base64_encoded };
dbgln_if(URL_PARSER_DEBUG, "URLParser::parse_data_url: Parsed data URL to be '{}'.", url.serialize());
return url;
}

40
Tests/AK/TestURL.cpp
View file

@ -1,5 +1,6 @@
/*
* Copyright (c) 2018-2020, Andreas Kling <kling@serenityos.org>
* Copyright (c) 2021, the SerenityOS developers.
*
* SPDX-License-Identifier: BSD-2-Clause
*/
@ -215,9 +216,22 @@ TEST_CASE(data_url)
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/html");
EXPECT_EQ(url.data_payload(), "test");
EXPECT(!url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/html,test");
}
TEST_CASE(data_url_default_mime_type)
{
URL url("data:,test");
EXPECT(url.is_valid());
EXPECT_EQ(url.scheme(), "data");
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/plain");
EXPECT_EQ(url.data_payload(), "test");
EXPECT(!url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/plain,test");
}
TEST_CASE(data_url_encoded)
{
URL url("data:text/html,Hello%20friends%2C%0X%X0");
@ -226,6 +240,7 @@ TEST_CASE(data_url_encoded)
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/html");
EXPECT_EQ(url.data_payload(), "Hello friends,%0X%X0");
EXPECT(!url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/html,Hello friends,%0X%X0");
}
@ -237,9 +252,34 @@ TEST_CASE(data_url_base64_encoded)
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/html");
EXPECT_EQ(url.data_payload(), "test");
EXPECT(url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/html;base64,test");
}
TEST_CASE(data_url_base64_encoded_default_mime_type)
{
URL url("data:;base64,test");
EXPECT(url.is_valid());
EXPECT_EQ(url.scheme(), "data");
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/plain");
EXPECT_EQ(url.data_payload(), "test");
EXPECT(url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/plain;base64,test");
}
TEST_CASE(data_url_base64_encoded_with_whitespace)
{
URL url("data: text/html ; bAsE64 , test with whitespace ");
EXPECT(url.is_valid());
EXPECT_EQ(url.scheme(), "data");
EXPECT(url.host().is_null());
EXPECT_EQ(url.data_mime_type(), "text/html");
EXPECT_EQ(url.data_payload(), " test with whitespace ");
EXPECT(url.data_payload_is_base64());
EXPECT_EQ(url.serialize(), "data:text/html;base64, test with whitespace ");
}
TEST_CASE(trailing_slash_with_complete_url)
{
EXPECT_EQ(URL("http://a/b/").complete_url("c/").serialize(), "http://a/b/c/");