sized/src/lib.rs

use byte_unit::{Byte, UnitType};

use clap::{CommandFactory, Parser, ValueEnum};
use clap_complete::{generate, Shell};
use colored::*;
use comfy_table::presets::UTF8_FULL;
use comfy_table::{Attribute, Cell, CellAlignment, Color, ContentArrangement, Table};
use csv::WriterBuilder;
use ignore::WalkBuilder;
use rayon::prelude::*;
use serde::Serialize;
use std::cmp::Ordering;
use std::io::Write;
use std::os::unix::fs::MetadataExt;
use std::path::{Path, PathBuf};
use std::str::FromStr;

#[derive(Parser, Debug, Clone)]
#[command(author, version, about, long_about = None)]
#[command(disable_version_flag = true)]
pub struct Args {
    /// Print version
    #[arg(short = 'v', long, action = clap::ArgAction::Version)]
    pub version: Option<bool>,

    /// Directory to analyze
    #[arg(default_value = ".")]
    pub path: PathBuf,

    /// Minimum size filter (e.g. "10MB", "1gb")
    #[arg(short = 'm', long)]
    pub min_size: Option<String>,

    /// Limit the number of results per table
    #[arg(short = 'n', long)]
    pub number: Option<usize>,

    /// Sort by columns (e.g. "type:asc,size:dsc").
    /// defaults to size:dsc.
    /// Columns: name, type, size, blocks.
    #[arg(long)]
    pub sort: Option<String>,

    /// Depth to traverse (0 = only immediate children)
    #[arg(short, long, default_value = "0")]
    pub depth: usize,

    /// Display full absolute paths
    #[arg(short = 'f', long, conflicts_with = "path_relative")]
    pub path_full: bool,

    /// Display paths relative to current directory (default)
    #[arg(long)]
    pub path_relative: bool,

    /// Number of threads to use (defaults to available logical CPUs)
    #[arg(short = 'j', long = "threads")]
    pub threads: Option<usize>,

    /// Generate shell completions
    #[arg(long, value_enum)]
    pub completions: Option<Shell>,

    /// Respect .gitignore and .ignore files
    #[arg(short = 'i', long)]
    pub ignore: bool,

    /// Output format
    #[arg(long, value_enum, default_value_t = OutputFormat::Text)]
    pub format: OutputFormat,

    /// Save output to file (optional filename, defaults to timestamped name)
    #[arg(long, num_args(0..=1), default_missing_value = "_AUTO_")]
    pub save: Option<PathBuf>,
}

#[derive(ValueEnum, Clone, Debug, PartialEq, Eq)]
pub enum OutputFormat {
    Text,
    Csv,
    Json,
}

#[derive(Debug, Clone, PartialEq, Eq)]
pub enum SortColumn {
    Name,
    Type,
    Size,
    Blocks,
}

impl FromStr for SortColumn {
    type Err = String;
    fn from_str(s: &str) -> Result<Self, Self::Err> {
        match s.to_lowercase().as_str() {
            "name" | "n" => Ok(SortColumn::Name),
            "type" | "t" => Ok(SortColumn::Type),
            "size" | "s" => Ok(SortColumn::Size),
            "blocks" | "b" => Ok(SortColumn::Blocks),
            _ => Err(format!("Unknown column: {}", s)),
        }
    }
}

#[derive(Debug, Clone, PartialEq, Eq)]
pub enum SortDirection {
    Asc,
    Dsc,
}

impl FromStr for SortDirection {
    type Err = String;
    fn from_str(s: &str) -> Result<Self, Self::Err> {
        match s.to_lowercase().as_str() {
            "asc" | "a" => Ok(SortDirection::Asc),
            "dsc" | "d" | "desc" => Ok(SortDirection::Dsc),
            _ => Err(format!("Unknown direction: {}", s)),
        }
    }
}

#[derive(Clone, Serialize, Debug)]
pub struct Node {
    pub path: PathBuf,
    pub size_bytes: u64,
    pub blocks: u64,
    pub entry_type: EntryType,
    #[serde(skip)]
    pub children: Vec<Node>,
}

#[derive(Clone, Serialize, Debug, PartialEq, Eq, PartialOrd, Ord)]
pub enum EntryType {
    File,
    Dir,
}

impl std::fmt::Display for EntryType {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        match self {
            EntryType::File => write!(f, "File"),
            EntryType::Dir => write!(f, "Dir"),
        }
    }
}

#[derive(Serialize)]
pub struct JsonMetrics {
    pub size_bytes: u64,
    pub blocks: u64,
}

#[derive(Serialize)]
pub struct JsonEntry<'a> {
    pub path: &'a PathBuf,
    pub metrics: JsonMetrics,
    pub entry_type: String,
}

#[derive(Serialize)]
pub struct JsonReport<'a> {
    pub path: &'a PathBuf,
    pub total_size: u64,
    pub blocks: u64,
    pub entries: Vec<JsonEntry<'a>>,
}

pub fn run(args: Args, mut writer: &mut dyn Write) {
    if let Some(shell) = args.completions {
        let mut cmd = Args::command();
        let name = cmd.get_name().to_string();
        generate(shell, &mut cmd, name, &mut std::io::stdout());
        return;
    }

    if let Some(threads) = args.threads {
        rayon::ThreadPoolBuilder::new()
            .num_threads(threads)
            .build_global()
            .ok(); // Ignore error if initialized called multiple times (e.g. in tests)
    }

    let target_path = args.path.clone();

    if !target_path.exists() {
        eprintln!("Error: Path '{}' does not exist.", target_path.display());
        std::process::exit(1);
    }

    let min_bytes = if let Some(size_str) = &args.min_size {
        match Byte::parse_str(size_str, true) {
            Ok(byte) => byte.as_u64(),
            Err(e) => {
                eprintln!("Error parsing size '{}': {}", size_str, e);
                std::process::exit(1);
            }
        }
    } else {
        0
    };

    let sort_criteria = parse_sort_arg(args.sort.as_deref().unwrap_or("size:dsc"));

    if args.format == OutputFormat::Csv {
        writeln!(writer, "Path,Type,Size(Bytes),Blocks").expect("Failed to write CSV header");
    }

    let root_node = build_tree(&target_path, args.ignore);

    if root_node.size_bytes < min_bytes {
        if args.format == OutputFormat::Text {
            writeln!(writer, "Root directory is smaller than minimum size.").ok();
        }
        return;
    }

    process_node_recursive(&mut writer, &root_node, 0, &args, min_bytes, &sort_criteria);
}

pub fn build_tree(path: &Path, ignore: bool) -> Node {
    let metadata = path.metadata();

    if let Ok(meta) = metadata {
        if meta.is_file() {
            return Node {
                path: path.to_path_buf(),
                size_bytes: meta.len(),
                blocks: meta.blocks(),
                entry_type: EntryType::File,
                children: vec![],
            };
        }
    }

    let walker = WalkBuilder::new(path)
        .standard_filters(false)
        .hidden(false)
        .git_ignore(ignore)
        .ignore(ignore)
        .max_depth(Some(1))
        .build();

    let child_paths: Vec<PathBuf> = walker
        .into_iter()
        .filter_map(|e| e.ok())
        .filter(|e| e.path() != path)
        .map(|e| e.path().to_path_buf())
        .collect();

    let children: Vec<Node> = child_paths
        .par_iter()
        .map(|p| build_tree(p, ignore))
        .collect();

    let (size_bytes, blocks) = children
        .iter()
        .fold((0, 0), |acc, c| (acc.0 + c.size_bytes, acc.1 + c.blocks));

    let (self_size, self_blocks) = path
        .metadata()
        .map(|m| (m.len(), m.blocks()))
        .unwrap_or((0, 0));

    Node {
        path: path.to_path_buf(),
        size_bytes: size_bytes + self_size,
        blocks: blocks + self_blocks,
        entry_type: EntryType::Dir,
        children,
    }
}

fn process_node_recursive(
    writer: &mut dyn Write,
    node: &Node,
    current_depth: usize,
    args: &Args,
    min_bytes: u64,
    sort_criteria: &[(SortColumn, SortDirection)],
) {
    if node.children.is_empty() && node.entry_type == EntryType::Dir {}

    let mut display_children: Vec<&Node> = node
        .children
        .iter()
        .filter(|c| c.size_bytes >= min_bytes)
        .collect();

    display_children.sort_by(|a, b| compare_nodes(a, b, sort_criteria));

    if let Some(n) = args.number {
        if n < display_children.len() {
            display_children.truncate(n);
        }
    }

    let show_relative = !args.path_full;
    let relative_path = if show_relative {
        let cwd = std::env::current_dir().unwrap_or_default();
        node.path
            .strip_prefix(&cwd)
            .unwrap_or(&node.path)
            .display()
            .to_string()
    } else {
        node.path
            .canonicalize()
            .unwrap_or(node.path.clone())
            .display()
            .to_string()
    };

    print_output(
        writer,
        &node,
        &display_children,
        args,
        &relative_path,
        current_depth,
    );

    if current_depth < args.depth {
        for child in display_children {
            if child.entry_type == EntryType::Dir {
                process_node_recursive(
                    writer,
                    child,
                    current_depth + 1,
                    args,
                    min_bytes,
                    sort_criteria,
                );
            }
        }
    }
}

pub fn compare_nodes(a: &Node, b: &Node, criteria: &[(SortColumn, SortDirection)]) -> Ordering {
    for (col, dir) in criteria {
        let order = match col {
            SortColumn::Name => a.path.file_name().cmp(&b.path.file_name()),
            SortColumn::Type => a.entry_type.cmp(&b.entry_type),
            SortColumn::Size => a.size_bytes.cmp(&b.size_bytes),
            SortColumn::Blocks => a.blocks.cmp(&b.blocks),
        };

        if order != Ordering::Equal {
            return match dir {
                SortDirection::Asc => order,
                SortDirection::Dsc => order.reverse(),
            };
        }
    }
    Ordering::Equal
}

pub fn parse_sort_arg(s: &str) -> Vec<(SortColumn, SortDirection)> {
    s.split(',')
        .filter_map(|part| {
            let parts: Vec<&str> = part.split(':').collect();
            if parts.is_empty() {
                return None;
            }

            let col_str = parts[0];
            let col = SortColumn::from_str(col_str).ok()?;

            let dir = if parts.len() > 1 {
                SortDirection::from_str(parts[1]).unwrap_or(SortDirection::Dsc)
            } else {
                match col {
                    SortColumn::Name | SortColumn::Type => SortDirection::Asc,
                    _ => SortDirection::Dsc,
                }
            };
            Some((col, dir))
        })
        .collect()
}

fn print_output(
    writer: &mut dyn Write,
    parent_node: &Node,
    children: &[&Node],
    args: &Args,
    relative_path: &str,
    depth: usize,
) {
    match args.format {
        OutputFormat::Text => print_text(writer, parent_node, children, relative_path, depth),
        OutputFormat::Csv => print_csv(writer, children),
        OutputFormat::Json => print_json(writer, parent_node, children),
    }
}

fn print_text(
    writer: &mut dyn Write,
    parent_node: &Node,
    children: &[&Node],
    relative_path: &str,
    depth: usize,
) {
    if depth > 0 {
        writeln!(writer, "{}", "-".repeat(60).dimmed()).ok();
    }
    writeln!(writer, "\n{}", relative_path.bold().blue()).ok();

    let total_byte = Byte::from_u64(parent_node.size_bytes);
    writeln!(
        writer,
        "Total size: {} / {} ({} blocks)",
        total_byte
            .get_appropriate_unit(UnitType::Binary)
            .to_string()
            .bold()
            .green(),
        parent_node.size_bytes.to_string().bold().green(),
        parent_node.blocks
    )
    .ok();

    if children.is_empty() {
        writeln!(writer, "(No children)").ok();
        return;
    }

    let mut table = Table::new();
    table
        .load_preset(UTF8_FULL)
        .set_content_arrangement(ContentArrangement::Dynamic)
        .set_header(vec![
            Cell::new("Name").add_attribute(Attribute::Bold),
            Cell::new("Type").add_attribute(Attribute::Bold),
            Cell::new("Size (Human)")
                .add_attribute(Attribute::Bold)
                .set_alignment(CellAlignment::Right),
            Cell::new("Size (Bytes)")
                .add_attribute(Attribute::Bold)
                .set_alignment(CellAlignment::Right),
            Cell::new("Blocks")
                .add_attribute(Attribute::Bold)
                .set_alignment(CellAlignment::Right),
        ]);

    for child in children {
        let name = child.path.file_name().unwrap_or_default().to_string_lossy();
        let color = if child.entry_type == EntryType::Dir {
            Color::Blue
        } else {
            Color::Cyan
        };

        let child_byte = Byte::from_u64(child.size_bytes);

        table.add_row(vec![
            Cell::new(name).fg(color),
            Cell::new(&child.entry_type).fg(Color::Yellow),
            Cell::new(
                child_byte
                    .get_appropriate_unit(UnitType::Binary)
                    .to_string(),
            )
            .fg(Color::Green)
            .set_alignment(CellAlignment::Right),
            Cell::new(child.size_bytes.to_string()) // Raw bytes instead of "Decimal" unit
                .fg(Color::Green)
                .set_alignment(CellAlignment::Right),
            Cell::new(child.blocks)
                .fg(Color::Green)
                .set_alignment(CellAlignment::Right),
        ]);
    }
    writeln!(writer, "{}", table).ok();
}

fn print_csv(writer: &mut dyn Write, children: &[&Node]) {
    let mut wtr = WriterBuilder::new().has_headers(false).from_writer(writer);

    for child in children {
        wtr.write_record(&[
            child.path.to_string_lossy().as_ref(),
            &child.entry_type.to_string(),
            &child.size_bytes.to_string(),
            &child.blocks.to_string(),
        ])
        .ok();
    }
    wtr.flush().ok();
}

fn print_json(writer: &mut dyn Write, parent_node: &Node, children: &[&Node]) {
    let entries_view: Vec<JsonEntry> = children
        .iter()
        .map(|c| JsonEntry {
            path: &c.path,
            metrics: JsonMetrics {
                size_bytes: c.size_bytes,
                blocks: c.blocks,
            },
            entry_type: c.entry_type.to_string(),
        })
        .collect();

    let report = JsonReport {
        path: &parent_node.path,
        total_size: parent_node.size_bytes,
        blocks: parent_node.blocks,
        entries: entries_view,
    };

    serde_json::to_writer(&mut *writer, &report).ok();
    writer.write_all(b"\n").ok();
}

#[cfg(test)]
mod tests {
    use super::*;
    use std::fs::File;
    use tempfile::TempDir;

    #[test]
    fn test_parse_sort_arg() {
        let criteria = parse_sort_arg("size:asc,name");
        assert_eq!(criteria.len(), 2);
        assert_eq!(criteria[0], (SortColumn::Size, SortDirection::Asc));
        assert_eq!(criteria[1], (SortColumn::Name, SortDirection::Asc)); // Default for Name is Asc
    }

    #[test]
    fn test_sort_defaults() {
        let criteria = parse_sort_arg("size");
        assert_eq!(criteria[0], (SortColumn::Size, SortDirection::Dsc)); // Default for Size is Dsc
    }

    #[test]
    fn test_build_tree() {
        let temp_dir = TempDir::new().unwrap();
        let file_path = temp_dir.path().join("test_file.txt");
        File::create(&file_path)
            .unwrap()
            .write_all(b"Hello")
            .unwrap();

        let node = build_tree(temp_dir.path(), false);

        assert_eq!(node.entry_type, EntryType::Dir);
        assert!(!node.children.is_empty());
        assert_eq!(node.children[0].path, file_path);
        // Size should be at least 5 bytes
        assert!(node.children[0].size_bytes >= 5);
    }
}