From 5357ec1473c8a44dd8e324b2c664951bf4306b5a Mon Sep 17 00:00:00 2001 From: George Bateman Date: Mon, 31 Jan 2022 23:49:16 +0000 Subject: [PATCH] (#93493) Add items from code review --- library/core/src/primitive_docs.rs | 54 ++++++++++++++++++++---------- library/std/src/primitive_docs.rs | 54 ++++++++++++++++++++---------- 2 files changed, 74 insertions(+), 34 deletions(-) diff --git a/library/core/src/primitive_docs.rs b/library/core/src/primitive_docs.rs index e8b4fffbdd2..b9d71178921 100644 --- a/library/core/src/primitive_docs.rs +++ b/library/core/src/primitive_docs.rs @@ -289,32 +289,52 @@ mod prim_never {} /// /// A `char` is a '[Unicode scalar value]', which is any '[Unicode code point]' /// other than a [surrogate code point]. This has a fixed numerical definition: -/// code points are in the range `'\0'` to `char::MAX` (`'\u{10FFFF}'`), inclusive. -/// Surrogate code points, used by UTF-16, are in the range U+D800 to U+DFFF. +/// code points are in the range 0 to 0x10FFFF, inclusive. +/// Surrogate code points, used by UTF-16, are in the range 0xD800 to 0xDFFF. /// /// No `char` may be constructed, whether as a literal or at runtime, that is not a /// Unicode scalar value: /// /// ```text -/// let forbidden_chars = [ -/// // Each of these is a compiler error -/// '\u{D800}', '\u{DFFF}', '\u{110000}', -/// -/// // Panics; from_u32 returns None. -/// char::from_u32(0xDE01).unwrap(), -/// -/// // Undefined behaviour -/// unsafe { char::from_u32_unchecked(0x110000) }, -/// ]; +/// // Each of these is a compiler error +/// ['\u{D800}', '\u{DFFF}', '\u{110000}']; /// ``` /// -/// Unicode is regularly updated. Many USVs are not currently assigned to a -/// character, but may be in the future ("reserved"); some will never be a character -/// ("noncharacters"); and some may be given different meanings by different users -/// ("private use"). +/// ```should_panic +/// // Panics; from_u32 returns None. +/// char::from_u32(0xDE01).unwrap(); +/// ``` +/// +/// ``` +/// // Undefined behaviour +/// unsafe { char::from_u32_unchecked(0x110000) }; +/// ``` +/// +/// USVs are also the exact set of values that may be encoded in UTF-8. Because +/// `char` values are USVs and `str` values are valid UTF-8, it is safe to store +/// any `char` in a `str` or read any character from a `str` as a `char`. +/// +/// The gap in valid `char` values is understood by the compiler, so in the +/// below example the two ranges are understood to cover the whole range of +/// possible `char` values and there is no error for a [non-exhaustive match]. +/// +/// ``` +/// let c: char = 'a'; +/// match c { +/// '\0' ..= '\u{D7FF}' => false, +/// '\u{E000}' ..= '\u{10FFFF}' => true, +/// }; +/// ``` +/// +/// All USVs are valid `char` values, but not all of them represent a real +/// character. Many USVs are not currently assigned to a character, but may be +/// in the future ("reserved"); some will never be a character +/// ("noncharacters"); and some may be given different meanings by different +/// users ("private use"). /// -/// [Unicode scalar value]: https://www.unicode.org/glossary/#unicode_scalar_value /// [Unicode code point]: https://www.unicode.org/glossary/#code_point +/// [Unicode scalar value]: https://www.unicode.org/glossary/#unicode_scalar_value +/// [non-exhaustive match]: ../book/ch06-02-match.html#matches-are-exhaustive /// [surrogate code point]: https://www.unicode.org/glossary/#surrogate_code_point /// /// # Representation diff --git a/library/std/src/primitive_docs.rs b/library/std/src/primitive_docs.rs index e8b4fffbdd2..b9d71178921 100644 --- a/library/std/src/primitive_docs.rs +++ b/library/std/src/primitive_docs.rs @@ -289,32 +289,52 @@ mod prim_never {} /// /// A `char` is a '[Unicode scalar value]', which is any '[Unicode code point]' /// other than a [surrogate code point]. This has a fixed numerical definition: -/// code points are in the range `'\0'` to `char::MAX` (`'\u{10FFFF}'`), inclusive. -/// Surrogate code points, used by UTF-16, are in the range U+D800 to U+DFFF. +/// code points are in the range 0 to 0x10FFFF, inclusive. +/// Surrogate code points, used by UTF-16, are in the range 0xD800 to 0xDFFF. /// /// No `char` may be constructed, whether as a literal or at runtime, that is not a /// Unicode scalar value: /// /// ```text -/// let forbidden_chars = [ -/// // Each of these is a compiler error -/// '\u{D800}', '\u{DFFF}', '\u{110000}', -/// -/// // Panics; from_u32 returns None. -/// char::from_u32(0xDE01).unwrap(), -/// -/// // Undefined behaviour -/// unsafe { char::from_u32_unchecked(0x110000) }, -/// ]; +/// // Each of these is a compiler error +/// ['\u{D800}', '\u{DFFF}', '\u{110000}']; /// ``` /// -/// Unicode is regularly updated. Many USVs are not currently assigned to a -/// character, but may be in the future ("reserved"); some will never be a character -/// ("noncharacters"); and some may be given different meanings by different users -/// ("private use"). +/// ```should_panic +/// // Panics; from_u32 returns None. +/// char::from_u32(0xDE01).unwrap(); +/// ``` +/// +/// ``` +/// // Undefined behaviour +/// unsafe { char::from_u32_unchecked(0x110000) }; +/// ``` +/// +/// USVs are also the exact set of values that may be encoded in UTF-8. Because +/// `char` values are USVs and `str` values are valid UTF-8, it is safe to store +/// any `char` in a `str` or read any character from a `str` as a `char`. +/// +/// The gap in valid `char` values is understood by the compiler, so in the +/// below example the two ranges are understood to cover the whole range of +/// possible `char` values and there is no error for a [non-exhaustive match]. +/// +/// ``` +/// let c: char = 'a'; +/// match c { +/// '\0' ..= '\u{D7FF}' => false, +/// '\u{E000}' ..= '\u{10FFFF}' => true, +/// }; +/// ``` +/// +/// All USVs are valid `char` values, but not all of them represent a real +/// character. Many USVs are not currently assigned to a character, but may be +/// in the future ("reserved"); some will never be a character +/// ("noncharacters"); and some may be given different meanings by different +/// users ("private use"). /// -/// [Unicode scalar value]: https://www.unicode.org/glossary/#unicode_scalar_value /// [Unicode code point]: https://www.unicode.org/glossary/#code_point +/// [Unicode scalar value]: https://www.unicode.org/glossary/#unicode_scalar_value +/// [non-exhaustive match]: ../book/ch06-02-match.html#matches-are-exhaustive /// [surrogate code point]: https://www.unicode.org/glossary/#surrogate_code_point /// /// # Representation