Sylpheed/crates/sylpheed-formats/examples/ratc_optless_children.rs

//! The 60 RATC children that carry no `opt ` block — do they lack it, or is our
//! window too small?
//!
//! [`ratc::parse`] now prefers the name a child's own `opt ` block states, and
//! falls back to the old backwards printable-run scan when there is no block
//! within 128 bytes. That fallback fires for 60 of the disc's 18 002 children
//! (0.3 %), and the reach of the finding in `docs/re/structures/ratc-child-names.md`
//! stops there: "whether they genuinely lack the block or sit past the search
//! window is not established".
//!
//! This settles that. For every child with no accepted block it reports
//!
//!   * whether an `opt ` tag exists at all further back, and how far;
//!   * which guard rejected a tag that WAS in the window (length, gap, charset);
//!   * the child's position in its bundle and its magic, in case the opt-less
//!     ones are structurally distinct (e.g. always the first child);
//!   * the raw bytes before the magic, so the fallback's answer can be judged.
//!
//!     cargo run -p sylpheed-formats --example ratc_optless_children -- <pak>...
use sylpheed_formats::{pak, ratc};

/// Why a child has no accepted `opt ` name. Mirrors `ratc::opt_name`'s guards
/// one for one, so a rejection here is the same rejection the parser made.
#[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Clone)]
enum Why {
    /// No `opt ` tag in the 128-byte window, and none anywhere before it either.
    NoTagAtAll,
    /// No tag in the window, but one exists further back, this many bytes away.
    TagBeyondWindow(usize),
    /// Tag found, but its BE32 length is 0 or > 64.
    BadLength(usize),
    /// Tag found, name ends more than 8 bytes before the magic — a neighbour's.
    GapTooBig(usize),
    /// Tag found, the named bytes are not all printable ASCII.
    NotGraphic,
}

/// The parser's own window.
const WINDOW: usize = 128;

fn classify(buf: &[u8], at: usize) -> Option<Why> {
    let lo = at.saturating_sub(WINDOW);
    let pos = match buf[lo..at].windows(4).rposition(|w| w == b"opt ") {
        Some(p) => lo + p,
        None => {
            // Widen to the whole buffer before the child: is it merely far away?
            return Some(match buf[..at].windows(4).rposition(|w| w == b"opt ") {
                Some(p) => Why::TagBeyondWindow(at - p),
                None => Why::NoTagAtAll,
            });
        }
    };
    let len = u32::from_be_bytes(buf.get(pos + 4..pos + 8)?.try_into().ok()?) as usize;
    if len == 0 || len > 64 || pos + 8 + len > at {
        return Some(Why::BadLength(len));
    }
    let gap = at - (pos + 8 + len);
    if gap > 8 {
        return Some(Why::GapTooBig(gap));
    }
    let s = String::from_utf8_lossy(&buf[pos + 8..pos + 8 + len]);
    if s.is_empty() || !s.chars().all(|c| c.is_ascii_graphic()) {
        return Some(Why::NotGraphic);
    }
    None // accepted — this child is not one of the 60
}

fn main() {
    let mut total = 0usize;
    let mut rows: Vec<(String, usize, usize, String, String, Why)> = Vec::new();
    let mut first_child_of_bundle = 0usize;
    for path in std::env::args().skip(1) {
        let Ok(ar) = pak::PakArchive::open(&path) else {
            continue;
        };
        let short = path.rsplit('/').next().unwrap_or(&path).to_string();
        let entries: Vec<_> = ar.entries().to_vec();
        for (ei, e) in entries.iter().enumerate() {
            let Ok(bytes) = ar.read(e) else { continue };
            let Some(kids) = ratc::parse(&bytes) else {
                continue;
            };
            for (ci, c) in kids.iter().enumerate() {
                total += 1;
                let Some(why) = classify(&bytes, c.offset) else {
                    continue;
                };
                if ci == 0 {
                    first_child_of_bundle += 1;
                }
                let lo = c.offset.saturating_sub(24);
                let hex = bytes[lo..c.offset]
                    .iter()
                    .map(|b| format!("{b:02x}"))
                    .collect::<Vec<_>>()
                    .join(" ");
                rows.push((short.clone(), ei, ci, c.name.clone(), hex, why));
            }
        }
    }
    println!("RATC children scanned          : {total}");
    println!("  with NO accepted `opt ` block: {}", rows.len());
    println!("  ... of which are child #0    : {first_child_of_bundle}");

    let mut by_why: std::collections::BTreeMap<String, usize> = Default::default();
    for r in &rows {
        let k = match &r.5 {
            Why::TagBeyondWindow(_) => "TagBeyondWindow".to_string(),
            Why::BadLength(_) => "BadLength".to_string(),
            Why::GapTooBig(_) => "GapTooBig".to_string(),
            other => format!("{other:?}"),
        };
        *by_why.entry(k).or_default() += 1;
    }
    println!("\nwhy, by cause:");
    for (k, n) in &by_why {
        println!("   {k:20} x{n}");
    }

    println!("\nevery occurrence (name is what the FALLBACK scan returned):");
    for (p, ei, ci, name, hex, why) in &rows {
        println!("   {p:28} entry {ei:4} child {ci:3}  {name:24} {why:?}");
        println!("      24 bytes before the magic: {hex}");
    }
}