diff --git a/lib/text-size/.github/workflows/ci.yaml b/lib/text-size/.github/workflows/ci.yaml new file mode 100644 index 0000000000..4538ca8479 --- /dev/null +++ b/lib/text-size/.github/workflows/ci.yaml @@ -0,0 +1,54 @@ +name: CI +on: + pull_request: + push: + branches: + - master + - staging + - trying + +env: + RUSTFLAGS: -D warnings + RUSTUP_MAX_RETRIES: 10 + CARGO_NET_RETRY: 10 + +jobs: + rust: + name: Rust + runs-on: ${{ matrix.os }} + + strategy: + fail-fast: false + matrix: + os: [ubuntu-latest, windows-latest, macos-latest] + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Install Rust toolchain + uses: actions-rs/toolchain@v1 + with: + toolchain: stable + profile: minimal + + - name: Test + run: cargo test --all-features + + rustdoc: + name: Docs + runs-on: ubuntu-latest + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Install Rust toolchain + uses: actions-rs/toolchain@v1 + with: + toolchain: nightly + profile: minimal + override: true + + - name: Rustdoc + run: cargo rustdoc --all-features -- -D warnings diff --git a/lib/text-size/.gitignore b/lib/text-size/.gitignore new file mode 100644 index 0000000000..693699042b --- /dev/null +++ b/lib/text-size/.gitignore @@ -0,0 +1,3 @@ +/target +**/*.rs.bk +Cargo.lock diff --git a/lib/text-size/CHANGELOG.md b/lib/text-size/CHANGELOG.md new file mode 100644 index 0000000000..0167599e55 --- /dev/null +++ b/lib/text-size/CHANGELOG.md @@ -0,0 +1,26 @@ +# Changelog + +## 1.1.0 + +* add `TextRange::ordering` method + +## 1.0.0 :tada: + +* the carate is renamed to `text-size` from `text_unit` + +Transition table: +- `TextUnit::of_char(c)` ⟹ `TextSize::of(c)` +- `TextUnit::of_str(s)` ⟹ `TextSize::of(s)` +- `TextUnit::from_usize(size)` ⟹ `TextSize::try_from(size).unwrap_or_else(|| panic!(_))` +- `unit.to_usize()` ⟹ `usize::from(size)` +- `TextRange::from_to(from, to)` ⟹ `TextRange::new(from, to)` +- `TextRange::offset_len(offset, size)` ⟹ `TextRange::from_len(offset, size)` +- `range.start()` ⟹ `range.start()` +- `range.end()` ⟹ `range.end()` +- `range.len()` ⟹ `range.len()` +- `range.is_empty()` ⟹ `range.is_empty()` +- `a.is_subrange(b)` ⟹ `b.contains_range(a)` +- `a.intersection(b)` ⟹ `a.intersect(b)` +- `a.extend_to(b)` ⟹ `a.cover(b)` +- `range.contains(offset)` ⟹ `range.contains(point)` +- `range.contains_inclusive(offset)` ⟹ `range.contains_inclusive(point)` diff --git a/lib/text-size/Cargo.toml b/lib/text-size/Cargo.toml new file mode 100644 index 0000000000..7882f7cc35 --- /dev/null +++ b/lib/text-size/Cargo.toml @@ -0,0 +1,25 @@ +[package] +name = "text-size" +version = "1.1.1" +edition = "2018" + +authors = [ + "Aleksey Kladov ", + "Christopher Durham (CAD97) " +] +description = "Newtypes for text offsets" +license = "MIT OR Apache-2.0" +repository = "https://github.com/rust-analyzer/text-size" +documentation = "https://docs.rs/text-size" + +[dependencies] +serde = { version = "1.0", optional = true, default_features = false } + +[dev-dependencies] +serde_test = "1.0" +static_assertions = "1.1" + +[[test]] +name = "serde" +path = "tests/serde.rs" +required-features = ["serde"] diff --git a/lib/text-size/LICENSE-APACHE b/lib/text-size/LICENSE-APACHE new file mode 100644 index 0000000000..16fe87b06e --- /dev/null +++ b/lib/text-size/LICENSE-APACHE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + +TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + +1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + +2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + +3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + +4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + +5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + +6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + +7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + +8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + +9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + +END OF TERMS AND CONDITIONS + +APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + +Copyright [yyyy] [name of copyright owner] + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/lib/text-size/LICENSE-MIT b/lib/text-size/LICENSE-MIT new file mode 100644 index 0000000000..31aa79387f --- /dev/null +++ b/lib/text-size/LICENSE-MIT @@ -0,0 +1,23 @@ +Permission is hereby granted, free of charge, to any +person obtaining a copy of this software and associated +documentation files (the "Software"), to deal in the +Software without restriction, including without +limitation the rights to use, copy, modify, merge, +publish, distribute, sublicense, and/or sell copies of +the Software, and to permit persons to whom the Software +is furnished to do so, subject to the following +conditions: + +The above copyright notice and this permission notice +shall be included in all copies or substantial portions +of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF +ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED +TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A +PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT +SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR +IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. diff --git a/lib/text-size/README.md b/lib/text-size/README.md new file mode 100644 index 0000000000..365b6028a3 --- /dev/null +++ b/lib/text-size/README.md @@ -0,0 +1,27 @@ +# text-size + +[![Build Status](https://travis-ci.org/matklad/text-size.svg?branch=master)](https://travis-ci.org/matklad/text-size) +[![Crates.io](https://img.shields.io/crates/v/text-size.svg)](https://crates.io/crates/text-size) +[![API reference](https://docs.rs/text-size/badge.svg)](https://docs.rs/text-size/) + + +A library that provides newtype wrappers for `u32` and `(u32, u32)` for use as text offsets. + +See the [docs](https://docs.rs/text-size/) for more. + +## License + +Licensed under either of + + * Apache License, Version 2.0 + ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0) + * MIT license + ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT) + +at your option. + +## Contribution + +Unless you explicitly state otherwise, any contribution intentionally submitted +for inclusion in the work by you, as defined in the Apache-2.0 license, shall be +dual licensed as above, without any additional terms or conditions. diff --git a/lib/text-size/bors.toml b/lib/text-size/bors.toml new file mode 100644 index 0000000000..932be8d090 --- /dev/null +++ b/lib/text-size/bors.toml @@ -0,0 +1,6 @@ +status = [ + "Rust (ubuntu-latest)", + "Rust (windows-latest)", + "Rust (macos-latest)", +] +delete_merged_branches = true diff --git a/lib/text-size/src/lib.rs b/lib/text-size/src/lib.rs new file mode 100644 index 0000000000..92bd36b192 --- /dev/null +++ b/lib/text-size/src/lib.rs @@ -0,0 +1,32 @@ +//! Newtypes for working with text sizes/ranges in a more type-safe manner. +//! +//! This library can help with two things: +//! * Reducing storage requirements for offsets and ranges, under the +//! assumption that 32 bits is enough. +//! * Providing standard vocabulary types for applications where text ranges +//! are pervasive. +//! +//! However, you should not use this library simply because you work with +//! strings. In the overwhelming majority of cases, using `usize` and +//! `std::ops::Range` is better. In particular, if you are publishing a +//! library, using only std types in the interface would make it more +//! interoperable. Similarly, if you are writing something like a lexer, which +//! produces, but does not *store* text ranges, then sticking to `usize` would +//! be better. +//! +//! Minimal Supported Rust Version: latest stable. + +#![forbid(unsafe_code)] +#![warn(missing_debug_implementations, missing_docs)] + +mod range; +mod size; +mod traits; + +#[cfg(feature = "serde")] +mod serde_impls; + +pub use crate::{range::TextRange, size::TextSize, traits::TextLen}; + +#[cfg(target_pointer_width = "16")] +compile_error!("text-size assumes usize >= u32 and does not work on 16-bit targets"); diff --git a/lib/text-size/src/range.rs b/lib/text-size/src/range.rs new file mode 100644 index 0000000000..9b981642d1 --- /dev/null +++ b/lib/text-size/src/range.rs @@ -0,0 +1,456 @@ +use cmp::Ordering; + +use { + crate::TextSize, + std::{ + cmp, fmt, + ops::{Add, AddAssign, Bound, Index, IndexMut, Range, RangeBounds, Sub, SubAssign}, + }, +}; + +/// A range in text, represented as a pair of [`TextSize`][struct@TextSize]. +/// +/// It is a logic error for `start` to be greater than `end`. +#[derive(Default, Copy, Clone, Eq, PartialEq, Hash)] +pub struct TextRange { + // Invariant: start <= end + start: TextSize, + end: TextSize, +} + +impl fmt::Debug for TextRange { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "{}..{}", self.start().raw, self.end().raw) + } +} + +impl TextRange { + /// Creates a new `TextRange` with the given `start` and `end` (`start..end`). + /// + /// # Panics + /// + /// Panics if `end < start`. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let start = TextSize::from(5); + /// let end = TextSize::from(10); + /// let range = TextRange::new(start, end); + /// + /// assert_eq!(range.start(), start); + /// assert_eq!(range.end(), end); + /// assert_eq!(range.len(), end - start); + /// ``` + #[inline] + pub const fn new(start: TextSize, end: TextSize) -> TextRange { + assert!(start.raw <= end.raw); + TextRange { start, end } + } + + /// Create a new `TextRange` with the given `offset` and `len` (`offset..offset + len`). + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let text = "0123456789"; + /// + /// let offset = TextSize::from(2); + /// let length = TextSize::from(5); + /// let range = TextRange::at(offset, length); + /// + /// assert_eq!(range, TextRange::new(offset, offset + length)); + /// assert_eq!(&text[range], "23456") + /// ``` + #[inline] + pub const fn at(offset: TextSize, len: TextSize) -> TextRange { + TextRange::new(offset, TextSize::new(offset.raw + len.raw)) + } + + /// Create a zero-length range at the specified offset (`offset..offset`). + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let point: TextSize; + /// # point = TextSize::from(3); + /// let range = TextRange::empty(point); + /// assert!(range.is_empty()); + /// assert_eq!(range, TextRange::new(point, point)); + /// ``` + #[inline] + pub const fn empty(offset: TextSize) -> TextRange { + TextRange { + start: offset, + end: offset, + } + } + + /// Create a range up to the given end (`..end`). + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let point: TextSize; + /// # point = TextSize::from(12); + /// let range = TextRange::up_to(point); + /// + /// assert_eq!(range.len(), point); + /// assert_eq!(range, TextRange::new(0.into(), point)); + /// assert_eq!(range, TextRange::at(0.into(), point)); + /// ``` + #[inline] + pub const fn up_to(end: TextSize) -> TextRange { + TextRange { + start: TextSize::new(0), + end, + } + } +} + +/// Identity methods. +impl TextRange { + /// The start point of this range. + #[inline] + pub const fn start(self) -> TextSize { + self.start + } + + /// The end point of this range. + #[inline] + pub const fn end(self) -> TextSize { + self.end + } + + /// The size of this range. + #[inline] + pub const fn len(self) -> TextSize { + // HACK for const fn: math on primitives only + TextSize { + raw: self.end().raw - self.start().raw, + } + } + + /// Check if this range is empty. + #[inline] + pub const fn is_empty(self) -> bool { + // HACK for const fn: math on primitives only + self.start().raw == self.end().raw + } +} + +/// Manipulation methods. +impl TextRange { + /// Check if this range contains an offset. + /// + /// The end index is considered excluded. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let (start, end): (TextSize, TextSize); + /// # start = 10.into(); end = 20.into(); + /// let range = TextRange::new(start, end); + /// assert!(range.contains(start)); + /// assert!(!range.contains(end)); + /// ``` + #[inline] + pub fn contains(self, offset: TextSize) -> bool { + self.start() <= offset && offset < self.end() + } + + /// Check if this range contains an offset. + /// + /// The end index is considered included. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let (start, end): (TextSize, TextSize); + /// # start = 10.into(); end = 20.into(); + /// let range = TextRange::new(start, end); + /// assert!(range.contains_inclusive(start)); + /// assert!(range.contains_inclusive(end)); + /// ``` + #[inline] + pub fn contains_inclusive(self, offset: TextSize) -> bool { + self.start() <= offset && offset <= self.end() + } + + /// Check if this range completely contains another range. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let larger = TextRange::new(0.into(), 20.into()); + /// let smaller = TextRange::new(5.into(), 15.into()); + /// assert!(larger.contains_range(smaller)); + /// assert!(!smaller.contains_range(larger)); + /// + /// // a range always contains itself + /// assert!(larger.contains_range(larger)); + /// assert!(smaller.contains_range(smaller)); + /// ``` + #[inline] + pub fn contains_range(self, other: TextRange) -> bool { + self.start() <= other.start() && other.end() <= self.end() + } + + /// The range covered by both ranges, if it exists. + /// If the ranges touch but do not overlap, the output range is empty. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// assert_eq!( + /// TextRange::intersect( + /// TextRange::new(0.into(), 10.into()), + /// TextRange::new(5.into(), 15.into()), + /// ), + /// Some(TextRange::new(5.into(), 10.into())), + /// ); + /// ``` + #[inline] + pub fn intersect(self, other: TextRange) -> Option { + let start = cmp::max(self.start(), other.start()); + let end = cmp::min(self.end(), other.end()); + if end < start { + return None; + } + Some(TextRange::new(start, end)) + } + + /// Extends the range to cover `other` as well. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// assert_eq!( + /// TextRange::cover( + /// TextRange::new(0.into(), 5.into()), + /// TextRange::new(15.into(), 20.into()), + /// ), + /// TextRange::new(0.into(), 20.into()), + /// ); + /// ``` + #[inline] + pub fn cover(self, other: TextRange) -> TextRange { + let start = cmp::min(self.start(), other.start()); + let end = cmp::max(self.end(), other.end()); + TextRange::new(start, end) + } + + /// Extends the range to cover `other` offsets as well. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// assert_eq!( + /// TextRange::empty(0.into()).cover_offset(20.into()), + /// TextRange::new(0.into(), 20.into()), + /// ) + /// ``` + #[inline] + pub fn cover_offset(self, offset: TextSize) -> TextRange { + self.cover(TextRange::empty(offset)) + } + + /// Add an offset to this range. + /// + /// Note that this is not appropriate for changing where a `TextRange` is + /// within some string; rather, it is for changing the reference anchor + /// that the `TextRange` is measured against. + /// + /// The unchecked version (`Add::add`) will _always_ panic on overflow, + /// in contrast to primitive integers, which check in debug mode only. + #[inline] + pub fn checked_add(self, offset: TextSize) -> Option { + Some(TextRange { + start: self.start.checked_add(offset)?, + end: self.end.checked_add(offset)?, + }) + } + + /// Subtract an offset from this range. + /// + /// Note that this is not appropriate for changing where a `TextRange` is + /// within some string; rather, it is for changing the reference anchor + /// that the `TextRange` is measured against. + /// + /// The unchecked version (`Sub::sub`) will _always_ panic on overflow, + /// in contrast to primitive integers, which check in debug mode only. + #[inline] + pub fn checked_sub(self, offset: TextSize) -> Option { + Some(TextRange { + start: self.start.checked_sub(offset)?, + end: self.end.checked_sub(offset)?, + }) + } + + /// Relative order of the two ranges (overlapping ranges are considered + /// equal). + /// + /// + /// This is useful when, for example, binary searching an array of disjoint + /// ranges. + /// + /// # Examples + /// + /// ``` + /// # use text_size::*; + /// # use std::cmp::Ordering; + /// + /// let a = TextRange::new(0.into(), 3.into()); + /// let b = TextRange::new(4.into(), 5.into()); + /// assert_eq!(a.ordering(b), Ordering::Less); + /// + /// let a = TextRange::new(0.into(), 3.into()); + /// let b = TextRange::new(3.into(), 5.into()); + /// assert_eq!(a.ordering(b), Ordering::Less); + /// + /// let a = TextRange::new(0.into(), 3.into()); + /// let b = TextRange::new(2.into(), 5.into()); + /// assert_eq!(a.ordering(b), Ordering::Equal); + /// + /// let a = TextRange::new(0.into(), 3.into()); + /// let b = TextRange::new(2.into(), 2.into()); + /// assert_eq!(a.ordering(b), Ordering::Equal); + /// + /// let a = TextRange::new(2.into(), 3.into()); + /// let b = TextRange::new(2.into(), 2.into()); + /// assert_eq!(a.ordering(b), Ordering::Greater); + /// ``` + #[inline] + pub fn ordering(self, other: TextRange) -> Ordering { + if self.end() <= other.start() { + Ordering::Less + } else if other.end() <= self.start() { + Ordering::Greater + } else { + Ordering::Equal + } + } +} + +impl Index for str { + type Output = str; + #[inline] + fn index(&self, index: TextRange) -> &str { + &self[Range::::from(index)] + } +} + +impl Index for String { + type Output = str; + #[inline] + fn index(&self, index: TextRange) -> &str { + &self[Range::::from(index)] + } +} + +impl IndexMut for str { + #[inline] + fn index_mut(&mut self, index: TextRange) -> &mut str { + &mut self[Range::::from(index)] + } +} + +impl IndexMut for String { + #[inline] + fn index_mut(&mut self, index: TextRange) -> &mut str { + &mut self[Range::::from(index)] + } +} + +impl RangeBounds for TextRange { + fn start_bound(&self) -> Bound<&TextSize> { + Bound::Included(&self.start) + } + + fn end_bound(&self) -> Bound<&TextSize> { + Bound::Excluded(&self.end) + } +} + +impl From for Range +where + T: From, +{ + #[inline] + fn from(r: TextRange) -> Self { + r.start().into()..r.end().into() + } +} + +macro_rules! ops { + (impl $Op:ident for TextRange by fn $f:ident = $op:tt) => { + impl $Op<&TextSize> for TextRange { + type Output = TextRange; + #[inline] + fn $f(self, other: &TextSize) -> TextRange { + self $op *other + } + } + impl $Op for &TextRange + where + TextRange: $Op, + { + type Output = TextRange; + #[inline] + fn $f(self, other: T) -> TextRange { + *self $op other + } + } + }; +} + +impl Add for TextRange { + type Output = TextRange; + #[inline] + fn add(self, offset: TextSize) -> TextRange { + self.checked_add(offset) + .expect("TextRange +offset overflowed") + } +} + +impl Sub for TextRange { + type Output = TextRange; + #[inline] + fn sub(self, offset: TextSize) -> TextRange { + self.checked_sub(offset) + .expect("TextRange -offset overflowed") + } +} + +ops!(impl Add for TextRange by fn add = +); +ops!(impl Sub for TextRange by fn sub = -); + +impl AddAssign for TextRange +where + TextRange: Add, +{ + #[inline] + fn add_assign(&mut self, rhs: A) { + *self = *self + rhs + } +} + +impl SubAssign for TextRange +where + TextRange: Sub, +{ + #[inline] + fn sub_assign(&mut self, rhs: S) { + *self = *self - rhs + } +} diff --git a/lib/text-size/src/serde_impls.rs b/lib/text-size/src/serde_impls.rs new file mode 100644 index 0000000000..a94bee9567 --- /dev/null +++ b/lib/text-size/src/serde_impls.rs @@ -0,0 +1,48 @@ +use { + crate::{TextRange, TextSize}, + serde::{de, Deserialize, Deserializer, Serialize, Serializer}, +}; + +impl Serialize for TextSize { + fn serialize(&self, serializer: S) -> Result + where + S: Serializer, + { + self.raw.serialize(serializer) + } +} + +impl<'de> Deserialize<'de> for TextSize { + fn deserialize(deserializer: D) -> Result + where + D: Deserializer<'de>, + { + u32::deserialize(deserializer).map(TextSize::from) + } +} + +impl Serialize for TextRange { + fn serialize(&self, serializer: S) -> Result + where + S: Serializer, + { + (self.start(), self.end()).serialize(serializer) + } +} + +impl<'de> Deserialize<'de> for TextRange { + #[allow(clippy::nonminimal_bool)] + fn deserialize(deserializer: D) -> Result + where + D: Deserializer<'de>, + { + let (start, end) = Deserialize::deserialize(deserializer)?; + if !(start <= end) { + return Err(de::Error::custom(format!( + "invalid range: {:?}..{:?}", + start, end + ))); + } + Ok(TextRange::new(start, end)) + } +} diff --git a/lib/text-size/src/size.rs b/lib/text-size/src/size.rs new file mode 100644 index 0000000000..c950d2edd0 --- /dev/null +++ b/lib/text-size/src/size.rs @@ -0,0 +1,173 @@ +use { + crate::TextLen, + std::{ + convert::TryFrom, + fmt, iter, + num::TryFromIntError, + ops::{Add, AddAssign, Sub, SubAssign}, + u32, + }, +}; + +/// A measure of text length. Also, equivalently, an index into text. +/// +/// This is a UTF-8 bytes offset stored as `u32`, but +/// most clients should treat it as an opaque measure. +/// +/// For cases that need to escape `TextSize` and return to working directly +/// with primitive integers, `TextSize` can be converted losslessly to/from +/// `u32` via [`From`] conversions as well as losslessly be converted [`Into`] +/// `usize`. The `usize -> TextSize` direction can be done via [`TryFrom`]. +/// +/// These escape hatches are primarily required for unit testing and when +/// converting from UTF-8 size to another coordinate space, such as UTF-16. +#[derive(Clone, Copy, Default, PartialEq, Eq, PartialOrd, Ord, Hash)] +pub struct TextSize { + pub(crate) raw: u32, +} + +impl fmt::Debug for TextSize { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "{}", self.raw) + } +} + +impl TextSize { + /// Creates a new instance of `TextSize` from a raw `u32`. + #[inline] + pub const fn new(raw: u32) -> TextSize { + TextSize { raw } + } + + /// The text size of some primitive text-like object. + /// + /// Accepts `char`, `&str`, and `&String`. + /// + /// # Examples + /// + /// ```rust + /// # use text_size::*; + /// let char_size = TextSize::of('🦀'); + /// assert_eq!(char_size, TextSize::from(4)); + /// + /// let str_size = TextSize::of("rust-analyzer"); + /// assert_eq!(str_size, TextSize::from(13)); + /// ``` + #[inline] + pub fn of(text: T) -> TextSize { + text.text_len() + } +} + +/// Methods to act like a primitive integer type, where reasonably applicable. +// Last updated for parity with Rust 1.42.0. +impl TextSize { + /// Checked addition. Returns `None` if overflow occurred. + #[inline] + pub const fn checked_add(self, rhs: TextSize) -> Option { + match self.raw.checked_add(rhs.raw) { + Some(raw) => Some(TextSize { raw }), + None => None, + } + } + + /// Checked subtraction. Returns `None` if overflow occurred. + #[inline] + pub const fn checked_sub(self, rhs: TextSize) -> Option { + match self.raw.checked_sub(rhs.raw) { + Some(raw) => Some(TextSize { raw }), + None => None, + } + } +} + +impl From for TextSize { + #[inline] + fn from(raw: u32) -> Self { + TextSize { raw } + } +} + +impl From for u32 { + #[inline] + fn from(value: TextSize) -> Self { + value.raw + } +} + +impl TryFrom for TextSize { + type Error = TryFromIntError; + #[inline] + fn try_from(value: usize) -> Result { + Ok(u32::try_from(value)?.into()) + } +} + +impl From for usize { + #[inline] + fn from(value: TextSize) -> Self { + value.raw as usize + } +} + +macro_rules! ops { + (impl $Op:ident for TextSize by fn $f:ident = $op:tt) => { + impl $Op for TextSize { + type Output = TextSize; + #[inline] + fn $f(self, other: TextSize) -> TextSize { + TextSize { raw: self.raw $op other.raw } + } + } + impl $Op<&TextSize> for TextSize { + type Output = TextSize; + #[inline] + fn $f(self, other: &TextSize) -> TextSize { + self $op *other + } + } + impl $Op for &TextSize + where + TextSize: $Op, + { + type Output = TextSize; + #[inline] + fn $f(self, other: T) -> TextSize { + *self $op other + } + } + }; +} + +ops!(impl Add for TextSize by fn add = +); +ops!(impl Sub for TextSize by fn sub = -); + +impl AddAssign for TextSize +where + TextSize: Add, +{ + #[inline] + fn add_assign(&mut self, rhs: A) { + *self = *self + rhs + } +} + +impl SubAssign for TextSize +where + TextSize: Sub, +{ + #[inline] + fn sub_assign(&mut self, rhs: S) { + *self = *self - rhs + } +} + +impl iter::Sum for TextSize +where + TextSize: Add, +{ + #[inline] + fn sum>(iter: I) -> TextSize { + iter.fold(0.into(), Add::add) + } +} diff --git a/lib/text-size/src/traits.rs b/lib/text-size/src/traits.rs new file mode 100644 index 0000000000..d0bb6c1f66 --- /dev/null +++ b/lib/text-size/src/traits.rs @@ -0,0 +1,36 @@ +use {crate::TextSize, std::convert::TryInto}; + +use priv_in_pub::Sealed; +mod priv_in_pub { + pub trait Sealed {} +} + +/// Primitives with a textual length that can be passed to [`TextSize::of`]. +pub trait TextLen: Copy + Sealed { + /// The textual length of this primitive. + fn text_len(self) -> TextSize; +} + +impl Sealed for &'_ str {} +impl TextLen for &'_ str { + #[inline] + fn text_len(self) -> TextSize { + self.len().try_into().unwrap() + } +} + +impl Sealed for &'_ String {} +impl TextLen for &'_ String { + #[inline] + fn text_len(self) -> TextSize { + self.as_str().text_len() + } +} + +impl Sealed for char {} +impl TextLen for char { + #[inline] + fn text_len(self) -> TextSize { + (self.len_utf8() as u32).into() + } +} diff --git a/lib/text-size/tests/auto_traits.rs b/lib/text-size/tests/auto_traits.rs new file mode 100644 index 0000000000..6e62369533 --- /dev/null +++ b/lib/text-size/tests/auto_traits.rs @@ -0,0 +1,18 @@ +use { + static_assertions::*, + std::{ + fmt::Debug, + hash::Hash, + marker::{Send, Sync}, + panic::{RefUnwindSafe, UnwindSafe}, + }, + text_size::*, +}; + +// auto traits +assert_impl_all!(TextSize: Send, Sync, Unpin, UnwindSafe, RefUnwindSafe); +assert_impl_all!(TextRange: Send, Sync, Unpin, UnwindSafe, RefUnwindSafe); + +// common traits +assert_impl_all!(TextSize: Copy, Debug, Default, Hash, Ord); +assert_impl_all!(TextRange: Copy, Debug, Default, Hash, Eq); diff --git a/lib/text-size/tests/constructors.rs b/lib/text-size/tests/constructors.rs new file mode 100644 index 0000000000..9ff4e19c62 --- /dev/null +++ b/lib/text-size/tests/constructors.rs @@ -0,0 +1,24 @@ +use text_size::TextSize; + +#[derive(Copy, Clone)] +struct BadRope<'a>(&'a [&'a str]); + +impl BadRope<'_> { + fn text_len(self) -> TextSize { + self.0.iter().copied().map(TextSize::of).sum() + } +} + +#[test] +fn main() { + let x: char = 'c'; + let _ = TextSize::of(x); + + let x: &str = "hello"; + let _ = TextSize::of(x); + + let x: &String = &"hello".into(); + let _ = TextSize::of(x); + + let _ = BadRope(&[""]).text_len(); +} diff --git a/lib/text-size/tests/indexing.rs b/lib/text-size/tests/indexing.rs new file mode 100644 index 0000000000..93ba3c7cab --- /dev/null +++ b/lib/text-size/tests/indexing.rs @@ -0,0 +1,8 @@ +use text_size::*; + +#[test] +fn main() { + let range = TextRange::default(); + _ = &""[range]; + _ = &String::new()[range]; +} diff --git a/lib/text-size/tests/main.rs b/lib/text-size/tests/main.rs new file mode 100644 index 0000000000..5e6b86d659 --- /dev/null +++ b/lib/text-size/tests/main.rs @@ -0,0 +1,76 @@ +use {std::ops, text_size::*}; + +fn size(x: u32) -> TextSize { + TextSize::from(x) +} + +fn range(x: ops::Range) -> TextRange { + TextRange::new(x.start.into(), x.end.into()) +} + +#[test] +fn sum() { + let xs: Vec = vec![size(0), size(1), size(2)]; + assert_eq!(xs.iter().sum::(), size(3)); + assert_eq!(xs.into_iter().sum::(), size(3)); +} + +#[test] +fn math() { + assert_eq!(size(10) + size(5), size(15)); + assert_eq!(size(10) - size(5), size(5)); +} + +#[test] +fn checked_math() { + assert_eq!(size(1).checked_add(size(1)), Some(size(2))); + assert_eq!(size(1).checked_sub(size(1)), Some(size(0))); + assert_eq!(size(1).checked_sub(size(2)), None); + assert_eq!(size(!0).checked_add(size(1)), None); +} + +#[test] +#[rustfmt::skip] +fn contains() { + assert!( range(2..4).contains_range(range(2..3))); + assert!( ! range(2..4).contains_range(range(1..3))); +} + +#[test] +fn intersect() { + assert_eq!(range(1..2).intersect(range(2..3)), Some(range(2..2))); + assert_eq!(range(1..5).intersect(range(2..3)), Some(range(2..3))); + assert_eq!(range(1..2).intersect(range(3..4)), None); +} + +#[test] +fn cover() { + assert_eq!(range(1..2).cover(range(2..3)), range(1..3)); + assert_eq!(range(1..5).cover(range(2..3)), range(1..5)); + assert_eq!(range(1..2).cover(range(4..5)), range(1..5)); +} + +#[test] +fn cover_offset() { + assert_eq!(range(1..3).cover_offset(size(0)), range(0..3)); + assert_eq!(range(1..3).cover_offset(size(1)), range(1..3)); + assert_eq!(range(1..3).cover_offset(size(2)), range(1..3)); + assert_eq!(range(1..3).cover_offset(size(3)), range(1..3)); + assert_eq!(range(1..3).cover_offset(size(4)), range(1..4)); +} + +#[test] +#[rustfmt::skip] +fn contains_point() { + assert!( ! range(1..3).contains(size(0))); + assert!( range(1..3).contains(size(1))); + assert!( range(1..3).contains(size(2))); + assert!( ! range(1..3).contains(size(3))); + assert!( ! range(1..3).contains(size(4))); + + assert!( ! range(1..3).contains_inclusive(size(0))); + assert!( range(1..3).contains_inclusive(size(1))); + assert!( range(1..3).contains_inclusive(size(2))); + assert!( range(1..3).contains_inclusive(size(3))); + assert!( ! range(1..3).contains_inclusive(size(4))); +} diff --git a/lib/text-size/tests/serde.rs b/lib/text-size/tests/serde.rs new file mode 100644 index 0000000000..874258a35f --- /dev/null +++ b/lib/text-size/tests/serde.rs @@ -0,0 +1,79 @@ +use {serde_test::*, std::ops, text_size::*}; + +fn size(x: u32) -> TextSize { + TextSize::from(x) +} + +fn range(x: ops::Range) -> TextRange { + TextRange::new(x.start.into(), x.end.into()) +} + +#[test] +fn size_serialization() { + assert_tokens(&size(00), &[Token::U32(00)]); + assert_tokens(&size(10), &[Token::U32(10)]); + assert_tokens(&size(20), &[Token::U32(20)]); + assert_tokens(&size(30), &[Token::U32(30)]); +} + +#[test] +fn range_serialization() { + assert_tokens( + &range(00..10), + &[ + Token::Tuple { len: 2 }, + Token::U32(00), + Token::U32(10), + Token::TupleEnd, + ], + ); + assert_tokens( + &range(10..20), + &[ + Token::Tuple { len: 2 }, + Token::U32(10), + Token::U32(20), + Token::TupleEnd, + ], + ); + assert_tokens( + &range(20..30), + &[ + Token::Tuple { len: 2 }, + Token::U32(20), + Token::U32(30), + Token::TupleEnd, + ], + ); + assert_tokens( + &range(30..40), + &[ + Token::Tuple { len: 2 }, + Token::U32(30), + Token::U32(40), + Token::TupleEnd, + ], + ); +} + +#[test] +fn invalid_range_deserialization() { + assert_tokens::( + &range(62..92), + &[ + Token::Tuple { len: 2 }, + Token::U32(62), + Token::U32(92), + Token::TupleEnd, + ], + ); + assert_de_tokens_error::( + &[ + Token::Tuple { len: 2 }, + Token::U32(92), + Token::U32(62), + Token::TupleEnd, + ], + "invalid range: 92..62", + ); +}