Merge remote-tracking branch 'upstream/main' into joining-type

components/casemap/src/internals.rs

@@ -713,7 +713,7 @@ pub(crate) struct ContextIterator<'a> {
 impl<'a> ContextIterator<'a> {
  // Returns a context iterator with the characters before
  // and after the character at a given index, given the preceding
- // string and the succeding string including the character itself
+ // string and the succeeding string including the character itself
  pub fn new(before: &'a str, char_and_after: &'a str) -> Self {
  let mut char_and_after = char_and_after.chars();
  char_and_after.next(); // skip the character itself

components/collator/src/elements.rs

@@ -265,7 +265,7 @@ pub(crate) enum Tag {
  /// Tag for a lead surrogate code unit.
  /// Optional optimization for UTF-16 string processing.
  /// Bits 31..10: Unused, 0.
- /// 9.. 8: =0: All associated supplementary code points are unassigned-implict.
+ /// 9.. 8: =0: All associated supplementary code points are unassigned-implicit.
  /// =1: All associated supplementary code points fall back to the base data.
  /// else: (Normally 2) Look up the data for the supplementary code point.
  /// Not used by ICU4X.
@@ -1980,7 +1980,7 @@ where
  // `head[len - 2]` isn't a leading zero.
  // * If `len == 1`: The loop condition is false, because
  // `head[len - 1]` isn't a leading zero, and `&&`
- // short-circuts, so the `head[len - 2]` access doesn't
+ // short-circuits, so the `head[len - 2]` access doesn't
  // occur.
  #[allow(clippy::indexing_slicing)]
  while head[len - 1] == 0 && head[len - 2] == 0 {

components/collator/src/options.rs

@@ -351,7 +351,7 @@ pub enum BackwardSecondLevel {
 /// [`core::cmp::Ordering::Less`] and [`core::cmp::Ordering::Greater`]), it is
 /// possible to check if a set of human-readable strings contains a full-string
 /// fuzzy match of a user-entered string, where "fuzzy" means case-insensitive and
-/// accent-insentive for scripts that have such concepts and something roughly
+/// accent-insensitive for scripts that have such concepts and something roughly
 /// similar for other scripts.
 ///
 /// Due to the very limited utility, ICU4X data does not include search collations

components/collator/tests/tests.rs

@@ -896,7 +896,7 @@ fn test_th_reordering() {
  // supplementary composition decomps to supplementary
  "\u{0E41}\u{1D15F}",
  // supplementary composition decomps to BMP
- "\u{0E41}\u{2F802}", /* omit bacward iteration tests
+ "\u{0E41}\u{2F802}", /* omit backward iteration tests
  * contraction bug
  * "\u{0E24}\u{0E41}",
  * TODO: Support contracting starters, then add more here */

components/datetime/src/fields/length.rs

@@ -214,7 +214,7 @@ impl TryFrom<u8> for FieldNumericOverrides {
 }
 
 impl FieldNumericOverrides {
- /// Conver this to the corresponding string code
+ /// Convert this to the corresponding string code
  pub fn as_str(self) -> &'static str {
  match self {
  Self::Hanidec => "hanidec",

components/locid_transform/src/fallback/mod.rs

@@ -19,7 +19,7 @@ mod algorithms;
 ///
 /// Note that this implementation performs some additional steps compared to the *UTS #35*
 /// algorithm. See *[the design doc]* for a detailed description and [#2243](
-/// https://github.com/unicode-org/icu4x/issues/2243) to track aligment with *UTS #35*.
+/// https://github.com/unicode-org/icu4x/issues/2243) to track alignment with *UTS #35*.
 ///
 /// If running fallback in a loop, use [`DataLocale::is_und()`] to break from the loop.
 ///

components/segmenter/src/complex/lstm/matrix.rs

@@ -37,7 +37,7 @@ impl<const D: usize> MatrixOwned<D> {
  }
  }
 
- /// Returns the tighly packed submatrix at _index_, or `None` if _index_ is out of range.
+ /// Returns the tightly packed submatrix at _index_, or `None` if _index_ is out of range.
  ///
  /// For example, if the matrix is 5x4x3, this function returns a matrix sized 4x3. If the
  /// matrix is 4x3, then this function returns a linear matrix of length 3.

components/segmenter/src/complex/lstm/mod.rs

@@ -325,7 +325,7 @@ mod tests {
  use serde::Deserialize;
 
  /// `TestCase` is a struct used to store a single test case.
- /// Each test case has two attributs: `unseg` which denots the unsegmented line, and `true_bies` which indicates the Bies
+ /// Each test case has two attributes: `unseg` which denotes the unsegmented line, and `true_bies` which indicates the Bies
  /// sequence representing the true segmentation.
  #[derive(PartialEq, Debug, Deserialize)]
  struct TestCase {

components/segmenter/src/provider/lstm.rs

@@ -180,7 +180,7 @@ impl<'data> LstmDataFloat32<'data> {
  }
 
  #[cfg(any(feature = "serde", feature = "datagen"))]
- /// Creates a LstmDataFloat32 with the given data. Fails if the matrix dimensions are inconsisent.
+ /// Creates a LstmDataFloat32 with the given data. Fails if the matrix dimensions are inconsistent.
  #[allow(clippy::too_many_arguments)] // constructor
  pub fn try_from_parts(
  model: ModelType,

docs/posts/20201015_ICU4X_Project_Announcement.md

@@ -61,7 +61,7 @@ Rust provides strong bindings to [WebAssembly](https://webassembly.org/), and we
 While it’s early to have exact scope settled, ICU4X aims to expose a superset of `ECMA-402` scope of APIs to a wide range of platforms such as:
 
 * Web Platform (V8, SpiderMonkey, JSC)
-* Software platforms (Fuschia, Gecko)
+* Software platforms (Fuchsia, Gecko)
 * Mobile OSes (iOS, Android)
 * Low-power OSes with alloc (WearOS, WatchOS)
 * Client-side toolkits (Flutter)

docs/proposals/pr002-hunkspace.md

@@ -702,7 +702,7 @@ already transferred:
 
 This proposal glosses over the gritty detail of setting up the two-way
 communication over a common context, such as cache invalidation, context
-cleaning and availability concerns. The designers would neeed to take them
+cleaning and availability concerns. The designers would need to take them
 into account when developing a production version of this proposal. The URI
 encoding approach still favors statically defined messaging where such
 messaging is viable.

docs/tutorials/cpp/properties.cpp

@@ -199,7 +199,7 @@ int main() {
  }
  mask = mask_mapper.get_strict("EverythingLol");
  if (mask != 0) {
- std::cout << "Expected no mask for nonexistant name `EverythingLol`, found " << mask << std::endl;
+ std::cout << "Expected no mask for nonexistent name `EverythingLol`, found " << mask << std::endl;
  result = 1;
  }
 

docs/tutorials/data_management.md

@@ -90,7 +90,7 @@ $ cargo add litemap
 $ cargo add zerovec
 ```
 
-We can use the generate code with the `include!` macro. The `impl_data_provider!` macro adds the generated implemenations to any type.
+We can use the generate code with the `include!` macro. The `impl_data_provider!` macro adds the generated implementations to any type.
 
 ```rust,compile_fail
 extern crate alloc; // required as my-data is written for #[no_std]

docs/tutorials/data_management_interactive.md

@@ -51,7 +51,7 @@ We also need to enable the `serde` feature on the `icu` crate to enable deserial
 cargo add icu --features serde
 ```
 
-Now, update the instatiation of the datetime formatter to load data from the blob if the
+Now, update the instantiation of the datetime formatter to load data from the blob if the
 locale is Chakma:
 
 ```rust

docs/tutorials/data_provider.md

@@ -255,7 +255,7 @@ assert_eq!(formatter.format_to_string(&100007i64.into()), "100🐮007");
 
 ## Accessing the Resolved Locale
 
-ICU4X objects do not store their "resolved locale" because that is not a well-defined concept. Components can load data from many sources, and fallbacks to parent locales or root does not necesarily mean that a locale is not supported.
+ICU4X objects do not store their "resolved locale" because that is not a well-defined concept. Components can load data from many sources, and fallbacks to parent locales or root does not necessarily mean that a locale is not supported.
 
 However, for environments that require this behavior, such as ECMA-402, the data provider can be instrumented to access the resolved locale from `DataResponseMetadata`, as shown in the following example.
 

experimental/components/Cargo.toml

@@ -93,4 +93,4 @@ path = "tests/transliterate/cldr.rs"
 
 [[test]]
 name = "units_test"
-path = "tests/unitsconversion/units_test.rs"
+path = "tests/units/units_test.rs"

experimental/components/src/lib.rs

@@ -21,7 +21,7 @@ pub mod personnames;
 pub mod relativetime;
 pub mod transliterate;
 pub mod unicodeset_parse;
-pub mod unitsconversion;
+pub mod units;
 
 #[doc(hidden)]
 // Compiled constructors look for the baked provider at crate::provider::Baked,
@@ -114,6 +114,6 @@ pub mod provider {
  super::relativetime::provider::ShortSecondRelativeTimeFormatDataV1Marker::KEY,
  super::relativetime::provider::ShortWeekRelativeTimeFormatDataV1Marker::KEY,
  super::relativetime::provider::ShortYearRelativeTimeFormatDataV1Marker::KEY,
- super::unitsconversion::provider::UnitsInfoV1Marker::KEY,
+ super::units::provider::UnitsInfoV1Marker::KEY,
  ];
 }

experimental/components/src/unitsconversion/converter.rs → experimental/components/src/units/converter.rs

@@ -2,7 +2,7 @@
 // called LICENSE at the top level of the ICU4X source tree
 // (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).
 
-use crate::unitsconversion::{
+use crate::units::{
  measureunit::{MeasureUnit, MeasureUnitParser},
  provider::{Base, MeasureUnitItem, SiPrefix, Sign, SignULE, UnitsInfoV1},
 };

experimental/components/src/unitsconversion/measureunit.rs → experimental/components/src/units/measureunit.rs

@@ -7,7 +7,7 @@ use smallvec::SmallVec;
 use zerotrie::ZeroTrieSimpleAscii;
 use zerovec::ZeroVec;
 
-use crate::unitsconversion::{
+use crate::units::{
  power::get_power,
  provider::{Base, MeasureUnitItem, SiPrefix},
  si_prefix::get_si_prefix,

experimental/components/src/unitsconversion/provider.rs → experimental/components/src/units/provider.rs

@@ -35,7 +35,7 @@ pub use crate::provider::Baked;
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 #[yoke(prove_covariance_manually)]
@@ -57,7 +57,7 @@ pub struct UnitsInfoV1<'data> {
 #[cfg_attr(
  feature = "datagen",
  derive(databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(
  feature = "datagen",
@@ -108,7 +108,7 @@ pub struct ConversionInfo<'data> {
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 #[derive(Copy, Clone, Debug, PartialOrd, Ord, PartialEq, Eq, Default)]
@@ -124,7 +124,7 @@ pub enum Sign {
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 #[derive(Copy, Clone, Debug, PartialOrd, Ord, PartialEq, Eq, Default)]
@@ -139,7 +139,7 @@ pub enum Exactness {
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 #[derive(Copy, Clone, Debug, PartialOrd, Ord, PartialEq, Eq, Default)]
@@ -162,7 +162,7 @@ pub enum Base {
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 pub struct MeasureUnitItem {
@@ -183,7 +183,7 @@ pub struct MeasureUnitItem {
 #[cfg_attr(
  feature = "datagen",
  derive(serde::Serialize, databake::Bake),
- databake(path = icu_experimental::unitsconversion::provider),
+ databake(path = icu_experimental::units::provider),
 )]
 #[cfg_attr(feature = "serde", derive(serde::Deserialize))]
 pub struct SiPrefix {

experimental/components/src/unitsconversion/si_prefix.rs → experimental/components/src/units/si_prefix.rs

@@ -4,7 +4,7 @@
 
 use zerotrie::ZeroTrieSimpleAscii;
 
-use crate::unitsconversion::provider::{Base, SiPrefix};
+use crate::units::provider::{Base, SiPrefix};
 
 /// The offset of the SI prefixes.
 /// NOTE:

experimental/components/tests/unitsconversion/units_test.rs → experimental/components/tests/units/units_test.rs

@@ -3,7 +3,7 @@
 // (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).
 
 use core::str::FromStr;
-use icu_experimental::unitsconversion::converter::ConverterFactory;
+use icu_experimental::units::converter::ConverterFactory;
 use num_bigint::BigInt;
 use num_rational::BigRational;
 use num_rational::Ratio;
@@ -64,7 +64,7 @@ fn test_cldr_unit_tests() {
  result: BigRational,
  }
 
- let data = std::fs::read_to_string("tests/unitsconversion/data/unitsTest.txt").unwrap();
+ let data = std::fs::read_to_string("tests/units/data/unitsTest.txt").unwrap();
  let tests: Vec<UnitsTest> = data
  .lines()
  .filter(|line| !line.starts_with('#') && !line.is_empty())
@@ -79,14 +79,14 @@ fn test_cldr_unit_tests() {
  })
  .collect();
 
- let store = icu_experimental::unitsconversion::provider::Baked::SINGLETON_UNITS_INFO_V1
+ let store = icu_experimental::units::provider::Baked::SINGLETON_UNITS_INFO_V1
  .units_conversion_trie
  .clone() // cheap since store is a borrowed ZeroVec
  .take_store();
 
  let payload_store = &ZeroTrieSimpleAscii::from_store(store);
  let converter_factory = ConverterFactory::from_payload(
- icu_experimental::unitsconversion::provider::Baked::SINGLETON_UNITS_INFO_V1,
+ icu_experimental::units::provider::Baked::SINGLETON_UNITS_INFO_V1,
  payload_store,
  );
  let parser = converter_factory.parser();
@@ -131,14 +131,14 @@ fn test_units_not_parsable() {
  "kilo-squared-meter",
  ];
 
- let store = icu_experimental::unitsconversion::provider::Baked::SINGLETON_UNITS_INFO_V1
+ let store = icu_experimental::units::provider::Baked::SINGLETON_UNITS_INFO_V1
  .units_conversion_trie
  .clone() // cheap since store is a borrowed ZeroVec
  .take_store();
 
  let payload_store = &ZeroTrieSimpleAscii::from_store(store);
  let converter_factory = ConverterFactory::from_payload(
- icu_experimental::unitsconversion::provider::Baked::SINGLETON_UNITS_INFO_V1,
+ icu_experimental::units::provider::Baked::SINGLETON_UNITS_INFO_V1,
  payload_store,
  );
  let parser = converter_factory.parser();