difflib: parsing modern rust

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "difflib"
-version = "0.4.0"
+version = "0.5.1"
 authors = ["Dima Kudosh <dimakudosh@gmail.com>"]
 description = "Port of Python's difflib library to Rust."
 documentation = "https://github.com/DimaKudosh/difflib/wiki"

README.md

@@ -8,7 +8,7 @@ Simply add difflib to your dependencies block in Cargo.toml
 
 ```rust
 [dependencies]
-difflib = "0.4.0"
+difflib = "0.5.1"
 ```
 
 ## Documentation

src/differ.rs

@@ -1,6 +1,6 @@
-use sequencematcher::SequenceMatcher;
+use crate::sequencematcher::SequenceMatcher;
 use std::cmp;
-use utils::{count_leading, str_with_similar_chars};
+use crate::utils::{count_leading, str_with_similar_chars};
 
 #[derive(Default)]
 pub struct Differ {
@@ -252,6 +252,15 @@ impl Differ {
         res
     }
 
+    fn split_at_char_boundary<'a>(line: &'a str, char_idx: usize) -> (&'a str, &'a str) {
+        let byte_idx = line
+            .char_indices()
+            .nth(char_idx)
+            .map(|(i, _)| i)
+            .unwrap_or(line.len());
+        line.split_at(byte_idx)
+    }
+
     fn qformat(
         &self,
         first_line: &str,
@@ -266,10 +275,10 @@ impl Differ {
             count_leading(first_line, '\t'),
             count_leading(second_line, '\t'),
         );
+        common = cmp::min(common, count_leading(second_tags.split_at(common).0, ' '));
         common = cmp::min(common, count_leading(first_tags.split_at(common).0, ' '));
-        common = cmp::min(common, count_leading(first_tags.split_at(common).0, ' '));
-        first_tags = first_tags.split_at(common).1.trim_right();
-        second_tags = second_tags.split_at(common).1.trim_right();
+        first_tags = Self::split_at_char_boundary(first_tags, common).1.trim_end();
+        second_tags = Self::split_at_char_boundary(second_tags, common).1.trim_end();
         let mut s = format!("- {}", first_line);
         res.push(s);
         if first_tags != "" {

src/lib.rs

@@ -2,10 +2,10 @@ pub mod differ;
 pub mod sequencematcher;
 mod utils;
 
-use sequencematcher::{Sequence, SequenceMatcher};
+use crate::sequencematcher::{Sequence, SequenceMatcher};
 use std::collections::HashMap;
 use std::fmt::Display;
-use utils::{format_range_context, format_range_unified};
+use crate::utils::{format_range_context, format_range_unified};
 
 pub fn get_close_matches<'a>(
     word: &str,

src/sequencematcher.rs

@@ -1,7 +1,7 @@
 use std::cmp::{max, min};
 use std::collections::HashMap;
 use std::hash::Hash;
-use utils::calculate_ratio;
+use crate::utils::calculate_ratio;
 
 #[derive(Debug, Clone, Copy, PartialEq, PartialOrd, Eq, Ord)]
 pub struct Match {
@@ -114,7 +114,7 @@ impl<'a, T: Sequence> SequenceMatcher<'a, T> {
         let second_sequence = self.second_sequence;
         let mut second_sequence_elements = HashMap::new();
         for (i, item) in second_sequence.iter().enumerate() {
-            let mut counter = second_sequence_elements
+            let counter = second_sequence_elements
                 .entry(item)
                 .or_insert_with(Vec::new);
             counter.push(i);

tests/tests.rs

@@ -133,6 +133,18 @@ fn test_differ_restore() {
     assert_eq!(second_text, Differ::restore(&diff, 2));
 }
 
+#[test]
+fn test_differ_compare_utf8() {
+    let first_text = vec!["\tcrab 🦀\n"];
+    let second_text = vec!["\tcrab 🦞\n"];
+    let differ = Differ::new();
+    let result = differ.compare(&first_text, &second_text).join("");
+    assert!(result.contains("🦀"));
+    assert!(result.contains("🦞"));
+    assert!(result.contains("? "));
+    assert!(result.contains("^"));
+}
+
 #[test]
 fn test_unified_diff() {
     let first_text = "one two three four".split(" ").collect::<Vec<&str>>();