mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-25 09:00:22 +00:00
a3e82eaad3
DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
102 lines
2.7 KiB
C++
102 lines
2.7 KiB
C++
/*
|
|
* Copyright (c) 2022, Andreas Kling <kling@serenityos.org>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#include <LibTest/TestCase.h>
|
|
|
|
#include <AK/String.h>
|
|
#include <AK/StringBuilder.h>
|
|
#include <AK/Try.h>
|
|
#include <AK/Utf8View.h>
|
|
#include <AK/Vector.h>
|
|
|
|
TEST_CASE(construct_empty)
|
|
{
|
|
String empty;
|
|
EXPECT(empty.is_empty());
|
|
EXPECT_EQ(empty.bytes().size(), 0u);
|
|
|
|
auto empty2 = MUST(String::from_utf8(""sv));
|
|
EXPECT(empty2.is_empty());
|
|
EXPECT_EQ(empty, empty2);
|
|
EXPECT_EQ(empty, ""sv);
|
|
}
|
|
|
|
TEST_CASE(short_strings)
|
|
{
|
|
#ifdef AK_ARCH_64_BIT
|
|
auto string = MUST(String::from_utf8("abcdefg"sv));
|
|
EXPECT_EQ(string.is_short_string(), true);
|
|
EXPECT_EQ(string.bytes().size(), 7u);
|
|
EXPECT_EQ(string.bytes_as_string_view(), "abcdefg"sv);
|
|
#else
|
|
auto string = MUST(String::from_utf8("abc"sv));
|
|
EXPECT_EQ(string.is_short_string(), true);
|
|
EXPECT_EQ(string.bytes().size(), 3u);
|
|
EXPECT_EQ(string.bytes_as_string_view(), "abc"sv);
|
|
#endif
|
|
}
|
|
|
|
TEST_CASE(long_strings)
|
|
{
|
|
auto string = MUST(String::from_utf8("abcdefgh"sv));
|
|
EXPECT_EQ(string.is_short_string(), false);
|
|
EXPECT_EQ(string.bytes().size(), 8u);
|
|
EXPECT_EQ(string.bytes_as_string_view(), "abcdefgh"sv);
|
|
}
|
|
|
|
TEST_CASE(substring)
|
|
{
|
|
auto superstring = MUST(String::from_utf8("Hello I am a long string"sv));
|
|
auto short_substring = MUST(superstring.substring_from_byte_offset(0, 5));
|
|
EXPECT_EQ(short_substring, "Hello"sv);
|
|
|
|
auto long_substring = MUST(superstring.substring_from_byte_offset(0, 10));
|
|
EXPECT_EQ(long_substring, "Hello I am"sv);
|
|
}
|
|
|
|
TEST_CASE(code_points)
|
|
{
|
|
auto string = MUST(String::from_utf8("🦬🪒"sv));
|
|
|
|
Vector<u32> code_points;
|
|
for (auto code_point : string.code_points())
|
|
code_points.append(code_point);
|
|
|
|
EXPECT_EQ(code_points[0], 0x1f9acu);
|
|
EXPECT_EQ(code_points[1], 0x1fa92u);
|
|
}
|
|
|
|
TEST_CASE(string_builder)
|
|
{
|
|
StringBuilder builder;
|
|
builder.append_code_point(0x1f9acu);
|
|
builder.append_code_point(0x1fa92u);
|
|
|
|
auto string = MUST(builder.to_string());
|
|
EXPECT_EQ(string, "🦬🪒"sv);
|
|
EXPECT_EQ(string.bytes().size(), 8u);
|
|
}
|
|
|
|
TEST_CASE(ak_format)
|
|
{
|
|
auto foo = MUST(String::formatted("Hello {}", MUST(String::from_utf8("friends"sv))));
|
|
EXPECT_EQ(foo, "Hello friends"sv);
|
|
}
|
|
|
|
TEST_CASE(replace)
|
|
{
|
|
{
|
|
auto haystack = MUST(String::from_utf8("Hello enemies"sv));
|
|
auto result = MUST(haystack.replace("enemies"sv, "friends"sv, ReplaceMode::All));
|
|
EXPECT_EQ(result, "Hello friends"sv);
|
|
}
|
|
|
|
{
|
|
auto base_title = MUST(String::from_utf8("anon@courage:~"sv));
|
|
auto result = MUST(base_title.replace("[*]"sv, "(*)"sv, ReplaceMode::FirstOnly));
|
|
EXPECT_EQ(result, "anon@courage:~"sv);
|
|
}
|
|
}
|