From 3cecb0b23a8408ccc8300337d0539ba8070c8fd7 Mon Sep 17 00:00:00 2001
From: Jason Orendorff <jorendorff@github.com>
Date: Wed, 13 Nov 2024 11:32:41 -0600
Subject: [PATCH] address review comments

---
 crates/string-offsets/Cargo.toml |  4 ++--
 crates/string-offsets/README.md  |  6 +++---
 crates/string-offsets/src/lib.rs | 12 +++++++-----
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/crates/string-offsets/Cargo.toml b/crates/string-offsets/Cargo.toml
index dabf4d3..7d60dd2 100644
--- a/crates/string-offsets/Cargo.toml
+++ b/crates/string-offsets/Cargo.toml
@@ -3,10 +3,10 @@ name = "string-offsets"
 authors = ["The blackbird team <support@github.com>"]
 version = "0.1.0"
 edition = "2021"
-description = "Offset calculator to convert between byte, char, and line offsets in a string."
+description = "Converts string offsets between UTF-8 bytes, UTF-16 code units, Unicode code points, and lines."
 repository = "https://github.com/github/rust-gems"
 license = "MIT"
-keywords = ["unicode", "string", "offsets", "positions", "interoperability"]
+keywords = ["unicode", "positions", "utf16", "characters", "lines"]
 categories = ["algorithms", "data-structures", "text-processing", "development-tools::ffi"]
 
 [dev-dependencies]
diff --git a/crates/string-offsets/README.md b/crates/string-offsets/README.md
index fd04fc6..7ad8c23 100644
--- a/crates/string-offsets/README.md
+++ b/crates/string-offsets/README.md
@@ -1,13 +1,13 @@
 # string-offsets
 
-Offset calculator to convert between byte, char, and line offsets in a string.
+Converts string offsets between UTF-8 bytes, UTF-16 code units, Unicode code points, and lines.
 
 Rust strings are UTF-8, but JavaScript has UTF-16 strings, and in Python, strings are sequences of
 Unicode code points. It's therefore necessary to adjust string offsets when communicating across
 programming language boundaries. [`StringOffsets`] does these adjustments.
 
-Each `StringOffsets` value contains offset information for a single string. [Building the data
-structure](StringOffsets::new) takes O(n) time and memory, but then each conversion is fast.
+Each `StringOffsets` instance contains offset information for a single string. [Building the data
+structure](StringOffsets::new) takes O(n) time and memory, but then most conversions are O(1).
 
 ["UTF-8 Conversions with BitRank"](https://adaptivepatchwork.com/2023/07/10/utf-conversion/) is a
 blog post explaining the implementation.
diff --git a/crates/string-offsets/src/lib.rs b/crates/string-offsets/src/lib.rs
index a24d45c..ee05e54 100644
--- a/crates/string-offsets/src/lib.rs
+++ b/crates/string-offsets/src/lib.rs
@@ -1,4 +1,4 @@
-//! Offset calculator to convert between byte, char, and line offsets in a string.
+//! Converts string offsets between UTF-8 bytes, UTF-16 code units, Unicode code points, and lines.
 //!
 //! # Example
 //!
@@ -17,7 +17,7 @@
 //! // ...but only 3 UTF-16 code units...
 //! assert_eq!(offsets.utf8_to_utf16(12), 8);
 //! assert_eq!(offsets.utf8_to_utf16(19), 11);
-//! // ...and only 2 Unicode characters.
+//! // ...and only 2 Unicode code points.
 //! assert_eq!(offsets.utf8s_to_chars(12..19), 8..10);
 //! ```
 //!
@@ -30,14 +30,16 @@ mod bitrank;
 
 use bitrank::{BitRank, BitRankBuilder};
 
-/// Offset calculator to convert between byte, char, and line offsets in a string.
+/// Converts positions within a given string between UTF-8 byte offsets (the usual in Rust), UTF-16
+/// code units, Unicode code points, and line numbers.
 ///
 /// Rust strings are UTF-8, but JavaScript has UTF-16 strings, and in Python, strings are sequences
 /// of Unicode code points. It's therefore necessary to adjust string offsets when communicating
 /// across programming language boundaries. [`StringOffsets`] does these adjustments.
 ///
-/// Each `StringOffsets` value contains offset information for a single string. [Building the
-/// data structure](StringOffsets::new) takes O(n) time and memory, but then each conversion is fast.
+/// Each `StringOffsets` instance contains offset information for a single string. [Building the
+/// data structure](StringOffsets::new) takes O(n) time and memory, but then most conversions are
+/// O(1).
 ///
 /// ["UTF-8 Conversions with BitRank"](https://adaptivepatchwork.com/2023/07/10/utf-conversion/)
 /// is a blog post explaining the implementation.