from https://codeberg.org/Mycellf/wordjoin

use std::{
    fs::File,
    io::{self, BufRead, BufReader, Read, Write},
    path::PathBuf,
};

use clap::{Parser, ValueEnum};
use icu_segmenter::{
    LineSegmenter, LineSegmenterBorrowed,
    options::{LineBreakOptions, LineBreakStrictness, LineBreakWordOption},
};

/// Insert utf-8 word joiners (U+2060) to prevent text from wrapping outside of whitespace characters.
#[derive(Parser)]
struct Args {
    /// Format and concatenate each file in stead of stdin
    file_paths: Vec<PathBuf>,

    /// Read stdin by line instead of all at once
    /// (sometimes worse for interactive use; files are always read by line)
    #[clap(short = 'l', long)]
    by_line: bool,

    /// See https://drafts.csswg.org/css-text-3/#line-break-property
    #[clap(short, long, default_value = "strict")]
    strictness: LineBreakStrictnessValues,
    /// See https://drafts.csswg.org/css-text-3/#word-break-property
    #[clap(short, long, default_value = "normal")]
    word_option: LineBreakWordOptionValues,

    /// Print this app's GNU GPL-3.0 license
    #[arg(short = 'L', long)]
    license: bool,

    /// Print this app's source code
    #[arg(short = 'S', long)]
    source: bool,
}

const WORD_JOINER: char = '\u{2060}';

fn main() -> io::Result<()> {
    let args = Args::parse();

    if args.source || args.license {
        if args.source {
            println!(
                "Cargo.toml:\n{config}\n\nsrc/main.rs:\n{source}\n\nREADME.md:\n{readme}",
                config = include_str!("../Cargo.toml"),
                source = include_str!("main.rs"),
                readme = include_str!("../README.md"),
            );
        }

        if args.license {
            println!("LICENSE:\n{}", include_str!("../LICENSE"));
        }

        return Ok(());
    }

    let mut options = LineBreakOptions::default();
    options.strictness = Some(args.strictness.into());
    options.word_option = Some(args.word_option.into());

    let segmenter = LineSegmenter::new_auto(options);

    let mut stdout = io::stdout().lock();

    if args.file_paths.is_empty() {
        let stdin = io::stdin();

        if args.by_line {
            join_text_by_lines(stdout, stdin, segmenter)?;
        } else {
            join_text_by_all(stdout, stdin, segmenter)?;
        }
    } else {
        for path in args.file_paths {
            let file = File::open(path)?;

            join_text_by_lines(&mut stdout, file, segmenter)?;
        }
    }

    Ok(())
}

fn join_text_by_lines(
    mut writer: impl Write,
    text: impl Read,
    segmenter: LineSegmenterBorrowed,
) -> io::Result<()> {
    for line in BufReader::new(text).lines() {
        let line = line?;

        join_text(&mut writer, &line, segmenter)?;
        writeln!(&mut writer)?;
    }

    Ok(())
}

fn join_text_by_all(
    writer: impl Write,
    mut text: impl Read,
    segmenter: LineSegmenterBorrowed,
) -> io::Result<()> {
    let mut input = String::new();
    text.read_to_string(&mut input)?;

    join_text(writer, &input, segmenter)?;

    Ok(())
}

fn join_text(
    mut writer: impl Write,
    text: &str,
    segmenter: LineSegmenterBorrowed,
) -> io::Result<()> {
    let mut segments = segmenter.segment_str(text).peekable();

    while let (Some(start), Some(&end)) = (segments.next(), segments.peek()) {
        let segment = &text[start..end];

        write!(writer, "{segment}")?;

        if end < text.len()
            && segment
                .chars()
                .next_back()
                .is_some_and(|end| !end.is_whitespace())
        {
            write!(writer, "{WORD_JOINER}")?;
        }
    }

    Ok(())
}

#[derive(Clone, ValueEnum)]
enum LineBreakStrictnessValues {
    Loose,
    Normal,
    Strict,
    Anywhere,
}

impl From<LineBreakStrictnessValues> for LineBreakStrictness {
    fn from(value: LineBreakStrictnessValues) -> Self {
        match value {
            LineBreakStrictnessValues::Loose => LineBreakStrictness::Loose,
            LineBreakStrictnessValues::Normal => LineBreakStrictness::Normal,
            LineBreakStrictnessValues::Strict => LineBreakStrictness::Strict,
            LineBreakStrictnessValues::Anywhere => LineBreakStrictness::Anywhere,
        }
    }
}

#[derive(Clone, ValueEnum)]
enum LineBreakWordOptionValues {
    Normal,
    BreakAll,
    KeepAll,
}

impl From<LineBreakWordOptionValues> for LineBreakWordOption {
    fn from(value: LineBreakWordOptionValues) -> Self {
        match value {
            LineBreakWordOptionValues::Normal => LineBreakWordOption::Normal,
            LineBreakWordOptionValues::BreakAll => LineBreakWordOption::BreakAll,
            LineBreakWordOptionValues::KeepAll => LineBreakWordOption::KeepAll,
        }
    }
}