From 4908017d59da8694b9ceaf743baf1163c1e19086 Mon Sep 17 00:00:00 2001 From: Alex Crichton Date: Wed, 10 Dec 2014 09:02:31 -0800 Subject: std: Stabilize the std::str module This commit starts out by consolidating all `str` extension traits into one `StrExt` trait to be included in the prelude. This means that `UnicodeStrPrelude`, `StrPrelude`, and `StrAllocating` have all been merged into one `StrExt` exported by the standard library. Some functionality is currently duplicated with the `StrExt` present in libcore. This commit also currently avoids any methods which require any form of pattern to operate. These functions will be stabilized via a separate RFC. Next, stability of methods and structures are as follows: Stable * from_utf8_unchecked * CowString - after moving to std::string * StrExt::as_bytes * StrExt::as_ptr * StrExt::bytes/Bytes - also made a struct instead of a typedef * StrExt::char_indices/CharIndices - CharOffsets was renamed * StrExt::chars/Chars * StrExt::is_empty * StrExt::len * StrExt::lines/Lines * StrExt::lines_any/LinesAny * StrExt::slice_unchecked * StrExt::trim * StrExt::trim_left * StrExt::trim_right * StrExt::words/Words - also made a struct instead of a typedef Unstable * from_utf8 - the error type was changed to a `Result`, but the error type has yet to prove itself * from_c_str - this function will be handled by the c_str RFC * FromStr - this trait will have an associated error type eventually * StrExt::escape_default - needs iterators at least, unsure if it should make the cut * StrExt::escape_unicode - needs iterators at least, unsure if it should make the cut * StrExt::slice_chars - this function has yet to prove itself * StrExt::slice_shift_char - awaiting conventions about slicing and shifting * StrExt::graphemes/Graphemes - this functionality may only be in libunicode * StrExt::grapheme_indices/GraphemeIndices - this functionality may only be in libunicode * StrExt::width - this functionality may only be in libunicode * StrExt::utf16_units - this functionality may only be in libunicode * StrExt::nfd_chars - this functionality may only be in libunicode * StrExt::nfkd_chars - this functionality may only be in libunicode * StrExt::nfc_chars - this functionality may only be in libunicode * StrExt::nfkc_chars - this functionality may only be in libunicode * StrExt::is_char_boundary - naming is uncertain with container conventions * StrExt::char_range_at - naming is uncertain with container conventions * StrExt::char_range_at_reverse - naming is uncertain with container conventions * StrExt::char_at - naming is uncertain with container conventions * StrExt::char_at_reverse - naming is uncertain with container conventions * StrVector::concat - this functionality may be replaced with iterators, but it's not certain at this time * StrVector::connect - as with concat, may be deprecated in favor of iterators Deprecated * StrAllocating and UnicodeStrPrelude have been merged into StrExit * eq_slice - compiler implementation detail * from_str - use the inherent parse() method * is_utf8 - call from_utf8 instead * replace - call the method instead * truncate_utf16_at_nul - this is an implementation detail of windows and does not need to be exposed. * utf8_char_width - moved to libunicode * utf16_items - moved to libunicode * is_utf16 - moved to libunicode * Utf16Items - moved to libunicode * Utf16Item - moved to libunicode * Utf16Encoder - moved to libunicode * AnyLines - renamed to LinesAny and made a struct * SendStr - use CowString<'static> instead * str::raw - all functionality is deprecated * StrExt::into_string - call to_string() instead * StrExt::repeat - use iterators instead * StrExt::char_len - use .chars().count() instead * StrExt::is_alphanumeric - use .chars().all(..) * StrExt::is_whitespace - use .chars().all(..) Pending deprecation -- while slicing syntax is being worked out, these methods are all #[unstable] * Str - while currently used for generic programming, this trait will be replaced with one of [], deref coercions, or a generic conversion trait. * StrExt::slice - use slicing syntax instead * StrExt::slice_to - use slicing syntax instead * StrExt::slice_from - use slicing syntax instead * StrExt::lev_distance - deprecated with no replacement Awaiting stabilization due to patterns and/or matching * StrExt::contains * StrExt::contains_char * StrExt::split * StrExt::splitn * StrExt::split_terminator * StrExt::rsplitn * StrExt::match_indices * StrExt::split_str * StrExt::starts_with * StrExt::ends_with * StrExt::trim_chars * StrExt::trim_left_chars * StrExt::trim_right_chars * StrExt::find * StrExt::rfind * StrExt::find_str * StrExt::subslice_offset --- src/libstd/sys/windows/os.rs | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'src/libstd/sys') diff --git a/src/libstd/sys/windows/os.rs b/src/libstd/sys/windows/os.rs index e2220b7b67b..e1016048e58 100644 --- a/src/libstd/sys/windows/os.rs +++ b/src/libstd/sys/windows/os.rs @@ -31,6 +31,16 @@ use libc::types::os::arch::extra::DWORD; const BUF_BYTES : uint = 2048u; +/// Return a slice of `v` ending at (and not including) the first NUL +/// (0). +pub fn truncate_utf16_at_nul<'a>(v: &'a [u16]) -> &'a [u16] { + match v.iter().position(|c| *c == 0) { + // don't include the 0 + Some(i) => v[..i], + None => v + } +} + pub fn errno() -> uint { use libc::types::os::arch::extra::DWORD; @@ -87,7 +97,7 @@ pub fn error_string(errnum: i32) -> String { return format!("OS Error {} (FormatMessageW() returned error {})", errnum, fm_err); } - let msg = String::from_utf16(::str::truncate_utf16_at_nul(&buf)); + let msg = String::from_utf16(truncate_utf16_at_nul(&buf)); match msg { Some(msg) => format!("OS Error {}: {}", errnum, msg), None => format!("OS Error {} (FormatMessageW() returned invalid UTF-16)", errnum), @@ -294,3 +304,30 @@ pub fn page_size() -> uint { return info.dwPageSize as uint; } } + +#[cfg(test)] +mod tests { + use super::truncate_utf16_at_nul; + + #[test] + fn test_truncate_utf16_at_nul() { + let v = []; + let b: &[u16] = &[]; + assert_eq!(truncate_utf16_at_nul(&v), b); + + let v = [0, 2, 3]; + assert_eq!(truncate_utf16_at_nul(&v), b); + + let v = [1, 0, 3]; + let b: &[u16] = &[1]; + assert_eq!(truncate_utf16_at_nul(&v), b); + + let v = [1, 2, 0]; + let b: &[u16] = &[1, 2]; + assert_eq!(truncate_utf16_at_nul(&v), b); + + let v = [1, 2, 3]; + let b: &[u16] = &[1, 2, 3]; + assert_eq!(truncate_utf16_at_nul(&v), b); + } +} -- cgit 1.4.1-3-g733a5