combined lib/cli

Cargo.lock

@@ -2,6 +2,17 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "atty"
+version = "0.2.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "autocfg"
 version = "1.1.0"
@@ -26,6 +37,15 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
 
+[[package]]
+name = "hermit-abi"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "indoc"
 version = "2.0.4"
@@ -54,6 +74,16 @@ dependencies = [
  "scopeguard",
 ]
 
+[[package]]
+name = "lyagushka"
+version = "1.1.0"
+dependencies = [
+ "atty",
+ "pyo3",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "memoffset"
 version = "0.9.0"
@@ -101,15 +131,6 @@ dependencies = [
  "unicode-ident",
 ]
 
-[[package]]
-name = "pyagushka"
-version = "1.1.0"
-dependencies = [
- "pyo3",
- "serde",
- "serde_json",
-]
-
 [[package]]
 name = "pyo3"
 version = "0.20.2"
@@ -267,6 +288,28 @@ version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
 
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
 [[package]]
 name = "windows-targets"
 version = "0.48.5"

Cargo.toml

@@ -1,17 +1,11 @@
 [package]
-name = "pyagushka"
+name = "lyagushka"
 version = "1.1.0"
 edition = "2021"
-
-[lib]
-name = "pyagushka"
 crate-type = ["cdylib"]
 
 [dependencies]
-pyo3 = "0.20.2"
+atty = "0.2.14"
+pyo3 = { version = "0.20.2", features = ["extension-module"] }
 serde = { version = "1.0.196", features = ["derive"] }
-serde_json = "1.0.113"
-
-[features]
-extension-module = ["pyo3/extension-module"]
-default = ["extension-module"]
+serde_json = "1.0.113"

src/lib.rs

@@ -34,7 +34,7 @@ impl Anomaly {
 }
 
 #[pyclass]
-struct Lyagushka {
+pub struct Lyagushka {
     dataset: Vec<i32>,
     anomalies: Vec<Anomaly>,
 }
@@ -154,7 +154,7 @@ impl Lyagushka {
 }
 
 #[pymodule]
-fn pyagushka(_py: Python, m: &PyModule) -> PyResult<()> {
+fn lyagushka(_py: Python, m: &PyModule) -> PyResult<()> {
     m.add_class::<Lyagushka>()?;
     Ok(())
 }

src/main.rs

@@ -0,0 +1,70 @@
+use std::fs::File;
+use std::io::{self, BufRead, BufReader, stdin};
+use std::env;
+use std::process;
+use lyagushka::Lyagushka;
+
+/// The entry point for the command-line tool that reads a dataset of integers from either a file or stdin,
+/// performs cluster and gap analysis using specified parameters, and prints the results as a JSON string.
+///
+/// This tool expects either a filename as an argument or a list of integers piped into stdin. It also requires
+/// two additional command-line arguments: a factor for adjusting clustering and gap detection thresholds,
+/// and a minimum cluster size. The tool reads the dataset, performs the analysis by identifying clusters
+/// and significant gaps, calculates z-scores for each, and prints the JSON-serialized results to stdout.
+///
+/// # Usage
+/// To read from a file:
+/// ```
+/// cargo run -- filename.txt 0.5 2
+/// ```
+///
+/// To read from stdin:
+/// ```
+/// echo "1\n2\n10\n20" | cargo run -- 0.5 2
+/// ```
+///
+/// # Arguments
+/// - A filename (if not receiving piped input) to read the dataset from.
+/// - `factor`: A floating-point value used to adjust the sensitivity of cluster and gap detection.
+/// - `min_cluster_size`: The minimum number of contiguous points required to be considered a cluster.
+///
+/// # Exit Codes
+/// - `0`: Success.
+/// - `1`: Incorrect usage or failure to parse the input data.
+///
+/// # Errors
+/// This tool will exit with an error if the required arguments are not provided, if the specified file cannot be opened,
+/// or if the input data cannot be parsed into integers.
+///
+/// # Note
+/// This function does not return a value but directly exits the process in case of failure.
+///
+fn main() -> io::Result<()> {
+    let args: Vec<String> = env::args().collect();
+
+    // Input handling
+    let dataset: Vec<i32> = if atty::is(atty::Stream::Stdin) {
+        if args.len() != 4 {
+            eprintln!("Usage: {} <filename> <factor> <min_cluster_size>", args[0]);
+            process::exit(1);
+        }
+        let filename = &args[1];
+        let file = File::open(filename)?;
+        BufReader::new(file).lines().filter_map(Result::ok)
+            .filter_map(|line| line.trim().parse::<i32>().ok()) // Directly parse to i32
+            .collect()
+    } else {
+        stdin().lock().lines().filter_map(Result::ok)
+            .filter_map(|line| line.trim().parse::<i32>().ok()) // Directly parse to i32
+            .collect()
+    };
+
+    let factor: f32 = args[args.len() - 2].parse().expect("Factor must be a float");
+    let min_cluster_size: usize = args[args.len() - 1].parse().expect("Min cluster size must be an integer");
+
+    // Analysis and output
+    let mut zhaba = Lyagushka::new(dataset);
+    println!("{}", zhaba.search(factor, min_cluster_size));
+
+    Ok(())
+}