Name the UTF-8 cut helpers after what they do to the buffer

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-11-17 16:43:55 +01:00
1 parent 04fbced73d
commit 31b51c95db
2 files changed
+10 -10

No files matched your search

+5 -5
View File
@@ -2282,11 +2282,11 @@ scan_number_done:
// the lexer reads bytes (wide characters arrive as UTF-8), so
// move both cuts to character boundaries to keep the message
// valid UTF-8; this only shortens the two parts
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(utf8_head_cut(chars.data(), shown));
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(length_without_partial_utf8_at_end(chars.data(), shown));
const auto tail_begin = chars.end() - static_cast<std::ptrdiff_t>(shown);
append_escaped(result, chars.begin(), head_end);
result += "...";
append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(utf8_tail_skip(&*tail_begin)), chars.end());
append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(partial_utf8_length_at_start(&*tail_begin)), chars.end());
}
else
{
@@ -2309,7 +2309,7 @@ scan_number_done:
Looks only at the last 4 of these characters: in valid UTF-8, at most 3
bytes of a character can be before the cut.
*/
static std::size_t utf8_head_cut(const char_type* data, const std::size_t n) noexcept
static std::size_t length_without_partial_utf8_at_end(const char_type* data, const std::size_t n) noexcept
{
std::size_t lead = n - 1;
while (lead > n - 4 && is_utf8_continuation(data[lead]))
@@ -2333,9 +2333,9 @@ scan_number_done:
return lead + length > n ? lead : n;
}
/// the number of UTF-8 continuation bytes (at most 3) at @a data, which
/// the number of UTF-8 continuation bytes (at most 3) at the start of @a data, which
/// belong to a character that begins before it
static std::size_t utf8_tail_skip(const char_type* data) noexcept
static std::size_t partial_utf8_length_at_start(const char_type* data) noexcept
{
std::size_t skip = 0;
while (skip < 3 && is_utf8_continuation(data[skip]))
+5 -5
View File
@@ -15785,11 +15785,11 @@ scan_number_done:
// the lexer reads bytes (wide characters arrive as UTF-8), so
// move both cuts to character boundaries to keep the message
// valid UTF-8; this only shortens the two parts
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(utf8_head_cut(chars.data(), shown));
const auto head_end = chars.begin() + static_cast<std::ptrdiff_t>(length_without_partial_utf8_at_end(chars.data(), shown));
const auto tail_begin = chars.end() - static_cast<std::ptrdiff_t>(shown);
append_escaped(result, chars.begin(), head_end);
result += "...";
append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(utf8_tail_skip(&*tail_begin)), chars.end());
append_escaped(result, tail_begin + static_cast<std::ptrdiff_t>(partial_utf8_length_at_start(&*tail_begin)), chars.end());
}
else
{
@@ -15812,7 +15812,7 @@ scan_number_done:
Looks only at the last 4 of these characters: in valid UTF-8, at most 3
bytes of a character can be before the cut.
*/
static std::size_t utf8_head_cut(const char_type* data, const std::size_t n) noexcept
static std::size_t length_without_partial_utf8_at_end(const char_type* data, const std::size_t n) noexcept
{
std::size_t lead = n - 1;
while (lead > n - 4 && is_utf8_continuation(data[lead]))
@@ -15836,9 +15836,9 @@ scan_number_done:
return lead + length > n ? lead : n;
}
/// the number of UTF-8 continuation bytes (at most 3) at @a data, which
/// the number of UTF-8 continuation bytes (at most 3) at the start of @a data, which
/// belong to a character that begins before it
static std::size_t utf8_tail_skip(const char_type* data) noexcept
static std::size_t partial_utf8_length_at_start(const char_type* data) noexcept
{
std::size_t skip = 0;
while (skip < 3 && is_utf8_continuation(data[skip]))