diff options
Diffstat (limited to 'crates/shirabe-symfony-string')
| -rw-r--r-- | crates/shirabe-symfony-string/src/unicode_string.rs | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/crates/shirabe-symfony-string/src/unicode_string.rs b/crates/shirabe-symfony-string/src/unicode_string.rs index 9048f77b..21117437 100644 --- a/crates/shirabe-symfony-string/src/unicode_string.rs +++ b/crates/shirabe-symfony-string/src/unicode_string.rs @@ -6,7 +6,7 @@ pub struct UnicodeString { } impl UnicodeString { - // TODO(phase-c): the real constructor runs `normalizer_normalize` (Unicode NFC normalization), + // TODO(unicode): the real constructor runs `normalizer_normalize` (Unicode NFC normalization), // which has no Rust std equivalent and would need a dedicated normalization implementation. // Normalization is skipped here, which is only correct for already-NFC input such as ASCII. pub fn new(string: &str) -> Self { @@ -15,7 +15,7 @@ impl UnicodeString { } } - // TODO(phase-c): ASCII-only provisional implementation. The faithful `width()` uses `wcswidth` + // TODO(unicode): ASCII-only provisional implementation. The faithful `width()` uses `wcswidth` // with the Unicode width tables to treat wide characters as width 2 and skip zero-width / // combining characters; here every character counts as width 1, correct only for ASCII. The // ANSI/control-character stripping driven by `ignore_ansi_decoration` is likewise not handled. @@ -34,7 +34,7 @@ impl UnicodeString { width } - // TODO(phase-c): the faithful `length()` uses `grapheme_strlen` (extended grapheme clusters), + // TODO(unicode): the faithful `length()` uses `grapheme_strlen` (extended grapheme clusters), // which needs Unicode segmentation tables with no Rust std equivalent and no permitted crate. // Approximated with the code-point count, exact only when no combining/multi-code-point // clusters are present (e.g. ASCII). @@ -42,7 +42,7 @@ impl UnicodeString { shirabe_php_shim::mb_strlen(&self.string, "UTF-8") } - // TODO(phase-c): the faithful `slice()` uses `grapheme_substr` (grapheme-cluster offsets), which + // TODO(unicode): the faithful `slice()` uses `grapheme_substr` (grapheme-cluster offsets), which // needs Unicode segmentation tables with no std equivalent and no permitted crate. Approximated // with code-point offsets via `mb_substr`, exact only without combining/multi-code-point clusters. pub fn slice(&self, start: i64, length: Option<i64>) -> Self { |