Initial commit

6 files changed, 442 insertions, 0 deletions

diff --git a/.dir-locals.el b/.dir-locals.el
new file mode 100644
index 0000000..853a60f
--- /dev/null
+++ b/.dir-locals.el
@@ -0,0 +1,4 @@
+;;; Directory Local Variables         -*- no-byte-compile: t; -*-
+;;; For more information see (info "(emacs) Directory Variables")
+
+((rust-mode . ((flycheck-rust-binary-name . "shuf-grp"))))
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ea8c4bf
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+/target
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..3fa7e00
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,214 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a23eb6b1614318a8071c9b2521f36b424b2c83db5eb3a0fead4a6c0809af6e61"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasip2",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.178"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"
+
+[[package]]
+name = "memchr"
+version = "2.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
+
+[[package]]
+name = "natord"
+version = "1.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "308d96db8debc727c3fd9744aac51751243420e46edf401010908da7f8d5e57c"
+
+[[package]]
+name = "ppv-lite86"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
+dependencies = [
+ "zerocopy",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.103"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ee95bc4ef87b8d5ba32e8b7714ccc834865276eab0aed5c9958d00ec45f49e8"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a338cc41d27e6cc6dce6cefc13a0729dfbb81c262b1f519331575dd80ef3067f"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "rand"
+version = "0.9.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
+dependencies = [
+ "rand_chacha",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
+dependencies = [
+ "getrandom",
+]
+
+[[package]]
+name = "regex"
+version = "1.12.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843bc0191f75f3e22651ae5f1e72939ab2f72a4bc30fa80a066bd66edefc24d4"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5276caf25ac86c8d810222b3dbb938e512c55c6831a10f3e6ed1c93b84041f1c"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
+
+[[package]]
+name = "shuf-grp"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "natord",
+ "rand",
+ "regex",
+ "xdg",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.111"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "390cc9a294ab71bdb1aa2e99d13be9c753cd2d7bd6560c77118597410c4d2e87"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
+
+[[package]]
+name = "wasip2"
+version = "1.0.1+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0562428422c63773dad2c345a1882263bbf4d65cf3f42e90921f787ef5ad58e7"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "wit-bindgen"
+version = "0.46.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"
+
+[[package]]
+name = "xdg"
+version = "3.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fb433233f2df9344722454bc7e96465c9d03bff9d77c248f9e7523fe79585b5"
+
+[[package]]
+name = "zerocopy"
+version = "0.8.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd74ec98b9250adb3ca554bdde269adf631549f51d8a8f8f0a10b50f1cb298c3"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8a8d209fdf45cf5138cbb5a506f6b52522a25afccc534d1475dad8e31105c6a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..3cb11b7
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,11 @@
+[package]
+name = "shuf-grp"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+xdg = "3.0.0"
+regex = "1.12.2"
+anyhow = "1.0.100"
+rand = "0.9.2"
+natord = "1.0.9"
diff --git a/src/config.rs b/src/config.rs
new file mode 100644
index 0000000..6564c84
--- /dev/null
+++ b/src/config.rs
@@ -0,0 +1,37 @@
+use std::collections::HashMap;
+use std::fs::File;
+use std::io::{self, BufRead};
+use std::path::Path;
+use std::path::PathBuf;
+
+pub fn load_groups(path: &PathBuf) -> io::Result<HashMap<String, Vec<String>>> {
+    let lines = read_lines(path)?;
+    let mut groups = HashMap::new();
+    let mut group_name = String::new();
+    for mut line in lines.map_while(Result::ok) {
+        line.truncate(line.trim_end().len());
+        if line.starts_with("#") || line.is_empty() {
+            continue;
+        }
+        if line.starts_with("[") && line.ends_with("]") {
+            group_name = line[1..line.len() - 2].to_string();
+            if !groups.contains_key(&group_name) {
+                groups.insert(group_name.clone(), vec![]);
+            }
+            continue;
+        }
+        if group_name.is_empty() {
+            groups.insert(group_name.clone(), vec![]);
+        }
+        groups.get_mut(&group_name).unwrap().push(line);
+    }
+    Ok(groups)
+}
+
+fn read_lines<P>(filename: P) -> io::Result<io::Lines<io::BufReader<File>>>
+where
+    P: AsRef<Path>,
+{
+    let file = File::open(filename)?;
+    Ok(io::BufReader::new(file).lines())
+}
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..87fd1a4
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,175 @@
+use anyhow::anyhow;
+use rand::seq::IndexedRandom;
+use regex::{Regex, RegexBuilder, RegexSet};
+use std::collections::HashMap;
+use std::io;
+use std::ops::Range;
+use std::path::PathBuf;
+
+mod config;
+
+struct Config {
+    patterns: Vec<Regex>,
+    set: RegexSet,
+}
+
+impl Config {
+    fn new(patterns: Vec<Regex>) -> Self {
+        let set = RegexSet::new(patterns.iter().map(|x| x.to_string())).unwrap();
+        Self { patterns, set }
+    }
+}
+
+struct Match {
+    line: String,
+    group: Range<usize>,
+}
+
+impl Match {
+    fn new(line: String, group: Range<usize>) -> Self {
+        Self { line, group }
+    }
+
+    fn prefix(&self) -> &str {
+        &self.line[0..self.group.start]
+    }
+
+    fn infix(&self) -> &str {
+        &self.line[self.group.clone()]
+    }
+
+    fn suffix(&self) -> &str {
+        &self.line[self.group.end..self.line.len()]
+    }
+}
+
+struct PatternGroup {
+    matches: Vec<Match>,
+}
+
+impl PatternGroup {
+    fn new(matches: Vec<Match>) -> Self {
+        Self { matches }
+    }
+
+    fn calculate_groups(&self) -> Vec<usize> {
+        let mut groups = Vec::with_capacity(self.matches.len());
+        groups.push(0);
+        for i in 1..self.matches.len() {
+            if self.matches[i - 1].prefix() != self.matches[i].prefix()
+                || self.matches[i - 1].suffix() != self.matches[i].suffix()
+            {
+                groups.push(i);
+            }
+        }
+        groups
+    }
+}
+
+fn load_config(path: &PathBuf) -> anyhow::Result<Config> {
+    if !path.try_exists()? {
+        return Ok(default_config());
+    }
+    let groups = config::load_groups(path)?;
+    if let Some(patterns_str) = groups.get("groups") {
+        let mut patterns_regex = Vec::with_capacity(patterns_str.len());
+        for pattern in patterns_str {
+            let regex = RegexBuilder::new(pattern).size_limit(42_000).build()?;
+            if regex.captures_len() != 1 {
+                return Err(anyhow!(
+                    "Invalid pattern {}, capture groups are not one",
+                    pattern
+                ));
+            }
+            patterns_regex.push(regex);
+        }
+        return Ok(Config::new(patterns_regex));
+    }
+    Ok(Config::new(vec![]))
+}
+
+fn default_config() -> Config {
+    Config::new(vec![Regex::new(r"part([0-9]+)").unwrap()])
+}
+
+fn get_group(config: &Config, input: &str) -> (i64, Range<usize>) {
+    if let Some(index) = config.set.matches(input).iter().next() {
+        return (
+            index as i64,
+            config.patterns[index]
+                .captures(input)
+                .unwrap()
+                .get(1)
+                .unwrap()
+                .range(),
+        );
+    }
+    (-1, 0..input.len())
+}
+
+fn print_group(matches: &[Match]) {
+    for m in matches {
+        println!("{}", m.line);
+    }
+}
+
+fn main() -> anyhow::Result<()> {
+    let xdg_dirs = xdg::BaseDirectories::new();
+    let config;
+    if let Some(config_path) = xdg_dirs.get_config_file("shuf-grp.conf") {
+        config = load_config(&config_path)
+            .unwrap_or_else(|err| panic!("Error parsing {}: {}", config_path.display(), err));
+    } else {
+        eprintln!("Using default config, create ~/.config/shuf-grp.conf");
+        config = default_config();
+    }
+
+    let stdin = io::stdin();
+    let mut groups = HashMap::new();
+    loop {
+        let mut buffer = String::new();
+        let bytes = stdin.read_line(&mut buffer)?;
+        if bytes == 0 {
+            break;
+        }
+        buffer.truncate(buffer.trim_end().len());
+        let (group, part) = get_group(&config, &buffer);
+        let m = Match::new(buffer, part);
+        if let std::collections::hash_map::Entry::Vacant(e) = groups.entry(group) {
+            e.insert(PatternGroup::new(vec![m]));
+        } else {
+            let pattern_group: &mut PatternGroup = groups.get_mut(&group).unwrap();
+            match pattern_group.matches.binary_search_by(|x| {
+                x.prefix().cmp(m.prefix()).then(
+                    x.suffix()
+                        .cmp(m.suffix())
+                        .then(natord::compare(x.infix(), m.infix())),
+                )
+            }) {
+                Ok(pos) => pattern_group.matches.insert(pos, m),
+                Err(pos) => pattern_group.matches.insert(pos, m),
+            }
+        }
+    }
+
+    let mut indexes = Vec::<(i64, Range<usize>)>::with_capacity(groups.len());
+
+    for pattern_group in groups.iter_mut() {
+        let groups = pattern_group.1.calculate_groups();
+        for i in 1..groups.len() {
+            indexes.push((*pattern_group.0, groups[i - 1]..groups[i]));
+        }
+        indexes.push((
+            *pattern_group.0,
+            groups[groups.len() - 1]..pattern_group.1.matches.len(),
+        ));
+    }
+
+    let mut rng = rand::rng();
+
+    for (group, range) in indexes.choose_multiple(&mut rng, indexes.len()) {
+        print_group(&groups.get(group).unwrap().matches[range.clone()]);
+    }
+
+    Ok(())
+}