AK: Add substring methods to Utf8View

This patch implements a Unicode-safe substring method, which can be used
when offset and length should be specified in actual characters instead
of bytes.

This can be used to mitigate issues where a string is split in the
middle of a UTF-8 multi-byte character, which leads to invalid UTF-8.

Furthermore, it implements to common shorthands for substring methods
which take only an offset and return the substring until the end of the
string.
This commit is contained in:
Max Wipfli 2021-05-17 21:04:37 +02:00 committed by Andreas Kling
parent 8c19c2f296
commit c1b452f754
Notes: sideshowbarker 2024-07-18 17:36:31 +09:00
2 changed files with 27 additions and 2 deletions

View file

@ -1,5 +1,6 @@
/*
* Copyright (c) 2019-2020, Sergey Bugaev <bugaevc@serenityos.org>
* Copyright (c) 2021, Max Wipfli <mail@maxwipfli.ch>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
@ -59,6 +60,25 @@ Utf8View Utf8View::substring_view(size_t byte_offset, size_t byte_length) const
return Utf8View { string };
}
Utf8View Utf8View::unicode_substring_view(size_t codepoint_offset, size_t codepoint_length) const
{
if (codepoint_length == 0)
return {};
size_t codepoint_index = 0, offset_in_bytes = 0;
for (auto iterator = begin(); !iterator.done(); ++iterator) {
if (codepoint_index == codepoint_offset)
offset_in_bytes = byte_offset_of(iterator);
if (codepoint_index == codepoint_offset + codepoint_length - 1) {
size_t length_in_bytes = byte_offset_of(++iterator) - offset_in_bytes;
return substring_view(offset_in_bytes, length_in_bytes);
}
++codepoint_index;
}
VERIFY_NOT_REACHED();
}
static inline bool decode_first_byte(
unsigned char byte,
size_t& out_code_point_length_in_bytes,

View file

@ -1,5 +1,6 @@
/*
* Copyright (c) 2019-2020, Sergey Bugaev <bugaevc@serenityos.org>
* Copyright (c) 2021, Max Wipfli <mail@maxwipfli.ch>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
@ -57,9 +58,13 @@ public:
const unsigned char* bytes() const { return begin_ptr(); }
size_t byte_length() const { return m_string.length(); }
size_t byte_offset_of(const Utf8CodepointIterator&) const;
Utf8View substring_view(size_t byte_offset, size_t byte_length) const;
bool is_empty() const { return m_string.is_empty(); }
Utf8View substring_view(size_t byte_offset, size_t byte_length) const;
Utf8View substring_view(size_t byte_offset) const { return substring_view(byte_offset, byte_length() - byte_offset); }
Utf8View unicode_substring_view(size_t codepoint_offset, size_t codepoint_length) const;
Utf8View unicode_substring_view(size_t codepoint_offset) const { return unicode_substring_view(codepoint_offset, length() - codepoint_offset); }
bool is_empty() const { return m_string.is_empty(); }
bool starts_with(const Utf8View&) const;
size_t iterator_offset(const Utf8CodepointIterator& it) const