Apply more lints

This commit is contained in:
Andras Schmelczer 2024-12-18 22:14:09 +00:00
commit 1e1dd7b877
No known key found for this signature in database
GPG key ID: FC8F2C3D3D1A718C
24 changed files with 61 additions and 63 deletions

View file

@ -1,4 +1,4 @@
use std::iter;
use core::iter;
#[cfg(feature = "serde")]
use serde::{Deserialize, Serialize};
@ -9,17 +9,17 @@ use crate::{
operation_transformation::merge_context::MergeContext,
tokenizer::{word_tokenizer::word_tokenizer, Tokenizer},
utils::{
merge_iters::MergeSorted, ordered_operation::OrderedOperation, side::Side,
merge_iters::MergeSorted as _, ordered_operation::OrderedOperation, side::Side,
string_builder::StringBuilder,
},
};
/// A sequence of operations that can be applied to a text document.
/// EditedText supports merging two sequences of operations using the
/// `EditedText` supports merging two sequences of operations using the
/// principle of Operational Transformation.
///
/// It's mainly created through the from_strings method, then merged with
/// another EditedText derived from the same original text and then applied to
/// It's mainly created through the `from_strings` method, then merged with
/// another `EditedText` derived from the same original text and then applied to
/// the original text to get the reconciled text of concurrent edits.
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone, PartialEq, Default)]
@ -32,13 +32,13 @@ where
}
impl<'a> EditedText<'a, String> {
/// Create an EditedText from the given original (old) and updated (new)
/// strings. The returned EditedText represents the changes from the
/// Create an `EditedText` from the given original (old) and updated (new)
/// strings. The returned `EditedText` represents the changes from the
/// original to the updated text. When the return value is applied to
/// the original text, it will result in the updated text. The default
/// word tokenizer is used to tokenize the text which splits the text on
/// whitespaces.
pub fn from_strings(original: &'a str, updated: &str) -> Self {
#[must_use] pub fn from_strings(original: &'a str, updated: &str) -> Self {
Self::from_strings_with_tokenizer(original, updated, &word_tokenizer)
}
}
@ -47,8 +47,8 @@ impl<'a, T> EditedText<'a, T>
where
T: PartialEq + Clone,
{
/// Create an EditedText from the given original (old) and updated (new)
/// strings. The returned EditedText represents the changes from the
/// Create an `EditedText` from the given original (old) and updated (new)
/// strings. The returned `EditedText` represents the changes from the
/// original to the updated text. When the return value is applied to
/// the original text, it will result in the updated text. The tokenizer
/// function is used to tokenize the text.
@ -167,7 +167,7 @@ where
result
}
/// Create a new EditedText with the given operations.
/// Create a new `EditedText` with the given operations.
/// The operations must be in the order in which they are meant to be
/// applied. The operations must not overlap.
fn new(text: &'a str, operations: Vec<OrderedOperation<T>>) -> Self {
@ -186,7 +186,7 @@ where
Self { text, operations }
}
pub fn merge(self, other: Self) -> Self {
#[must_use] pub fn merge(self, other: Self) -> Self {
debug_assert_eq!(
self.text, other.text,
"EditedTexts must be derived from the same text to be mergable"
@ -207,7 +207,7 @@ where
operation.order,
// Operations on left and right must come in the same order so that
// inserts can be merged with other inserts and deletes with deletes.
matches!(operation.operation, Operation::Delete { .. }) as usize,
usize::from(matches!(operation.operation, Operation::Delete { .. })),
)
},
)
@ -233,9 +233,9 @@ where
///
/// # Errors
///
/// Returns an SyncLibError::OperationError if the operations cannot be
/// Returns an `SyncLibError::OperationError` if the operations cannot be
/// applied to the text.
pub fn apply(&self) -> String {
#[must_use] pub fn apply(&self) -> String {
let mut builder: StringBuilder<'_> = StringBuilder::new(self.text);
for OrderedOperation { operation, .. } in &self.operations {

View file

@ -1,4 +1,4 @@
use std::fmt::Debug;
use core::fmt::Debug;
use crate::operation_transformation::Operation;
@ -27,7 +27,7 @@ impl<T> Debug for MergeContext<T>
where
T: PartialEq + Clone,
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
f.debug_struct("MergeContext")
.field("last_operation", &self.last_operation)
.field("shift", &self.shift)

View file

@ -1,198 +0,0 @@
mod edited_text;
mod merge_context;
mod operation;
pub use edited_text::EditedText;
pub use operation::Operation;
use crate::tokenizer::Tokenizer;
pub fn reconcile(original: &str, left: &str, right: &str) -> String {
if left == right {
return left.to_string();
}
if original == left {
return right.to_string();
}
if original == right {
return left.to_string();
}
let left_operations = EditedText::from_strings(original, left);
let right_operations = EditedText::from_strings(original, right);
let merged_operations = left_operations.merge(right_operations);
merged_operations.apply()
}
pub fn reconcile_with_tokenizer<F, T>(
original: &str,
left: &str,
right: &str,
tokenizer: &Tokenizer<T>,
) -> String
where
T: PartialEq + Clone,
{
let left_operations = EditedText::from_strings_with_tokenizer(original, left, tokenizer);
let right_operations = EditedText::from_strings_with_tokenizer(original, right, tokenizer);
let merged_operations = left_operations.merge(right_operations);
merged_operations.apply()
}
#[cfg(test)]
mod test {
use std::{fs, ops::Range, path::Path};
use pretty_assertions::assert_eq;
use test_case::test_matrix;
use super::*;
#[test]
fn test_merges() {
// Both replaced one token but different
test_merge_both_ways(
"original_1 original_2 original_3",
"original_1 edit_1 original_3",
"original_1 original_2 edit_2",
"original_1 edit_1 edit_2",
);
// Both replaced the same one token
test_merge_both_ways(
"original_1 original_2 original_3",
"original_1 edit_1 original_3",
"original_1 edit_1 original_3",
"original_1 edit_1 original_3",
);
// One deleted a large range, the other deleted subranges and inserted as well
test_merge_both_ways(
"original_1 original_2 original_3 original_4 original_5",
"original_1 original_5",
"original_1 edit_1 original_3 edit_2 original_5",
"original_1 edit_1 edit_2 original_5",
);
// One deleted a large range, the other inserted and deleted a partially
// overlapping range
test_merge_both_ways(
"original_1 original_2 original_3 original_4 original_5",
"original_1 original_5",
"original_1 edit_1 original_3 edit_2",
"original_1 edit_1 edit_2",
);
// Merge a replace and an append
test_merge_both_ways("a b ", "c d ", "a b c d ", "c d c d ");
test_merge_both_ways("a b c d e", "a e", "a c e", "a e");
test_merge_both_ways("a 0 1 2 b", "a b", "a E 1 F b", "a E F b");
test_merge_both_ways(
"a this one delete b",
"a b",
"a my one change b",
"a my change b",
);
test_merge_both_ways(
"this stays, this is one big delete, don't touch this",
"this stays, don't touch this",
"this stays, my one change, don't touch this",
"this stays, my change, don't touch this",
);
test_merge_both_ways("1 2 3 4 5 6", "1 6", "1 2 4 ", "1 ");
test_merge_both_ways(
"hello world",
"hi, world",
"hello my friend!",
"hi, my friend!",
);
// test_merge_both_ways("hello world", "world !", "hi hello world", "hi world
// !");
test_merge_both_ways(
"both delete the same word",
"both the same word",
"both the same word",
"both the same word",
);
test_merge_both_ways(" ", "its utf-8!", " ", "its utf-8!");
test_merge_both_ways(
"both delete the same word but one a bit more",
"both the same word",
"both same word",
"both same word",
);
test_merge_both_ways(
"long text with one big delete and many small",
"long small",
"long with big and small",
"long small",
);
}
#[test_matrix( [
"pride_and_prejudice.txt",
"romeo_and_juliet.txt",
"room_with_a_view.txt",
"kun_lu.txt",
], [
"pride_and_prejudice.txt",
"romeo_and_juliet.txt",
"room_with_a_view.txt",
"kun_lu.txt"
], [
"pride_and_prejudice.txt",
"romeo_and_juliet.txt",
"room_with_a_view.txt",
"kun_lu.txt"
], [0..10000, 10000..20000], [0..10000, 10000..20000], [0..10000, 10000..20000])]
fn test_merge_files_without_panic(
file_name_1: &str,
file_name_2: &str,
file_name_3: &str,
range_1: Range<usize>,
range_2: Range<usize>,
range_3: Range<usize>,
) {
let files = [file_name_1, file_name_2, file_name_3];
let permutations = [range_1, range_2, range_3];
let root = Path::new("test/resources/");
let contents = files
.iter()
.zip(permutations.iter())
.map(|(file, range)| {
let path = root.join(file);
fs::read_to_string(&path)
.unwrap()
.chars()
.skip(range.start)
.take(range.end)
.collect::<String>()
})
.collect::<Vec<_>>();
reconcile(&contents[0], &contents[1], &contents[2]);
}
fn test_merge_both_ways(original: &str, edit_1: &str, edit_2: &str, expected: &str) {
assert_eq!(reconcile(original, edit_1, edit_2), expected);
assert_eq!(reconcile(original, edit_2, edit_1), expected);
}
}

View file

@ -1,4 +1,4 @@
use std::{
use core::{
fmt::{Debug, Display},
ops::Range,
};
@ -13,8 +13,8 @@ use crate::{
};
/// Represents a change that can be applied to a text document.
/// Operation is tied to a ropey::Rope and is mainly expected to be
/// created by EditedText.
/// Operation is tied to a `ropey::Rope` and is mainly expected to be
/// created by `EditedText`.
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Clone, PartialEq)]
pub enum Operation<T>
@ -81,12 +81,12 @@ where
})
}
/// Tries to apply the operation to the given ropey::Rope text, returning
/// Tries to apply the operation to the given `ropey::Rope` text, returning
/// the modified text.
///
/// # Errors
///
/// Returns a SyncLibError::OperationApplicationError if the operation
/// Returns a `SyncLibError::OperationApplicationError` if the operation
/// cannot be applied.
///
/// # Panics
@ -99,7 +99,7 @@ where
self.start_index(),
&text
.iter()
.map(|token| token.original())
.map(super::super::tokenizer::token::Token::original)
.collect::<String>(),
),
Operation::Delete {
@ -111,8 +111,7 @@ where
debug_assert!(
deleted_text
.as_ref()
.map(|text| builder.get_slice(self.range()) == *text)
.unwrap_or(true),
.map_or(true, |text| builder.get_slice(self.range()) == *text),
"Text to delete does not match the text in the rope"
);
@ -141,15 +140,16 @@ where
}
/// Returns the range of indices of characters that the operation affects.
pub fn range(&self) -> Range<usize> { self.start_index()..self.end_index() + 1 }
pub fn range(&self) -> Range<usize> { self.start_index()..self.end_index() - 1 }
/// Returns the number of affected characters. It is always greater than 0
/// because empty operations cannot be created.
pub fn len(&self) -> usize {
match self {
Operation::Insert { text, .. } => {
text.iter().map(|token| token.get_original_length()).sum()
}
Operation::Insert { text, .. } => text
.iter()
.map(super::super::tokenizer::token::Token::get_original_length)
.sum(),
Operation::Delete {
deleted_character_count,
..
@ -223,7 +223,7 @@ where
let trimmed_length = previous_inserted_text
.iter()
.skip(offset_in_tokens)
.map(|token| token.get_original_length())
.map(super::super::tokenizer::token::Token::get_original_length)
.sum::<usize>();
let trimmed_operation =
Operation::create_insert(index, text[trimmed_length_in_tokens..].to_vec());
@ -231,7 +231,7 @@ where
affecting_context.shift -= trimmed_length as i64;
produced_context.shift += trimmed_operation
.as_ref()
.map(|op| op.len())
.map(Operation::len)
.unwrap_or_default() as i64;
produced_context.consume_and_replace_last_operation(trimmed_operation.clone());
@ -305,14 +305,14 @@ impl<T> Display for Operation<T>
where
T: PartialEq + Clone,
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
match self {
Operation::Insert { index, text } => {
write!(
f,
"<insert '{}' from index {}>",
text.iter()
.map(|token| token.original())
.map(super::super::tokenizer::token::Token::original)
.collect::<String>(),
index
)
@ -351,7 +351,7 @@ impl<T> Debug for Operation<T>
where
T: PartialEq + Clone,
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result { write!(f, "{}", self) }
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { write!(f, "{self}") }
}
#[cfg(test)]