Modernize dependencies and Unicode support

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+  - package-ecosystem: cargo
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 5

.github/workflows/ci.yml

@@ -0,0 +1,21 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: clippy, rustfmt
+      - run: cargo fmt --all -- --check
+      - run: cargo clippy --all-targets --all-features -- -D warnings
+      - run: cargo test --all-features
+      - run: cargo bench --no-run

Cargo.toml

@@ -1,9 +1,10 @@
 [package]
 name = "common_substrings"
-description = "Finding all common strings"
+description = "Find common substrings across a collection of strings"
 version = "1.0.0"
 authors = ["hanwencheng <heawen.cheng@gmail.com>"]
-edition = "2018"
+edition = "2024"
+rust-version = "1.86"
 license = "Apache-2.0"
 readme = "README.md"
 homepage = "https://github.com/hanwencheng/common_substrings_rust"
@@ -12,7 +13,7 @@ repository = "https://github.com/hanwencheng/common_substrings_rust"
 [dependencies]
 
 [dev-dependencies]
-criterion = "0.3"
+criterion = "0.8.2"
 
 [[bench]]
 name = "benchmark"

README.md

@@ -1,14 +1,14 @@
 # Find all common substrings
 
-![versom](https://img.shields.io/crates/v/common_substrings)
+![crates.io version](https://img.shields.io/crates/v/common_substrings)
 
 A method for finding all common strings. Check it on [Crates.io](https://crates.io/crates/common_substrings).
 
-The algorithms uses a two dimension trie to get all the fragment. The vertical one is the standard suffix trie, but all the node of the last word in each suffix is linked, which I call them virtually horizontally linked.
+The algorithm uses a two-dimensional trie to find the fragments. The vertical dimension is a standard suffix trie; nodes at the end of each suffix are also linked horizontally.
 
 ## Usage
 
-Use the function `get_substrings` to get all the common strings in the strings list,
+Use `get_substrings` to get the common substrings in a list of strings.
 
 ### Example
 ```rust
@@ -17,7 +17,7 @@ let input_strings = vec!["java", "javascript", "typescript", "coffeescript", "co
 let result_substrings = get_substrings(input_strings, 2, 3);
 ```
 
-which gives the result list of 
+This produces results such as:
 ```shell
 Substring(sources: {2, 3}, name: escript, weight: 14)
 Substring(sources: {1, 0}, name: java, weight: 8)
@@ -26,9 +26,13 @@ Substring(sources: {4, 3}, name: coffee, weight: 12)
 
 ### Arguments
 
-* `input` - The target input string vector.
-* `min_occurrences` The minimal occurrence of the captured common substrings.
-* `min_length` The minimal length of the captured common substrings.
+* `input` — The input strings.
+* `min_occurrences` — The minimum number of input strings containing a result.
+* `min_length` — The minimum result length, measured in Unicode scalar values.
+
+Both thresholds must be positive. When `min_occurrences` exceeds the input size, the result is empty.
+
+The minimum supported Rust version is 1.86.
 
 ## Algorithm
 

benches/benchmark.rs

@@ -1,18 +1,27 @@
-use criterion::{criterion_group, criterion_main, Criterion};
 use common_substrings::get_substrings;
+use criterion::{Criterion, criterion_group, criterion_main};
+use std::hint::black_box;
 
-fn criterion_benchmark(c: &mut Criterion) {
-    c.bench_function("get substring", |b| b.iter(|| get_substrings(vec![
-        "java", 
-        "offe", 
-        "coffescript", 
-        "typescript", 
-        "typed", 
-        "javacoffie",
-        "fessss",
-        "fe",
-    ], 2, 3)));
+fn criterion_benchmark(criterion: &mut Criterion) {
+    criterion.bench_function("get substring", |bencher| {
+        bencher.iter(|| {
+            get_substrings(
+                black_box(vec![
+                    "java",
+                    "offe",
+                    "coffescript",
+                    "typescript",
+                    "typed",
+                    "javacoffie",
+                    "fessss",
+                    "fe",
+                ]),
+                2,
+                3,
+            )
+        })
+    });
 }
 
 criterion_group!(benches, criterion_benchmark);
-criterion_main!(benches);
+criterion_main!(benches);