Files
Sylpheed/crates/sylpheed-formats/examples/iso_map.rs
Fabian Hamm c4c914ff59
Some checks failed
CI / Native — linux (pull_request) Successful in 32m7s
CI / WASM — Web (pull_request) Failing after 8m3s
CI / Formatting (pull_request) Successful in 50s
style: rustfmt sweep -- 774 hunks across 154 files -> 0
`cargo fmt --all -- --check` has failed on every run in this repository's
history, identically on `main` and on every branch. This is #12.

Mechanical: `cargo fmt --all`, nothing else. 154 files, all `.rs`, no other
extension touched. `cargo check --workspace` exits 0 afterwards, so nothing
changed semantically.

ON THE ORDERING, WHICH WAS THE REAL QUESTION.

HANDOFF-2026-09-06 section 7 warns this is the expensive fix: a whole-tree
reformat before #7 and #8 return "would put a conflict in every file of 861
commits and make the reviews those items exist to enable unreadable".

That is measurably too pessimistic, and it had been reasoned rather than
tested. Measured here by three-way merging a rustfmt'd `main` against both
unmerged branches, file by file:

  file/branch pairs tested   32
  merges CLEAN               28
  merges CONFLICTING          4   (8 conflict hunks total)

    sylpheed-cli/src/main.rs      1 hunk
    sylpheed-export/src/check.rs  1
    sylpheed-export/src/screen.rs 4
    sylpheed-export/src/video.rs  2

All four are against `auto/frame-blend-draw-path` only;
`auto/port-p6-audio` does not conflict anywhere. The earlier framing --
154 dirty files, 133 that cannot collide, 21 that can, the collision set
carrying 147 of 774 hunks (19%) -- reproduces exactly. What it did not say
is that most of the 21 still merge cleanly, because rustfmt's edits and the
branches' edits rarely land on the same lines.

So the cost of sweeping now is 4 files and 8 hunks for one branch, against
a check that is otherwise red forever. Deliberately NOT folded into the
WASM PR: 154 reformatted files would make that one unreviewable.

Closes #12
2026-09-08 20:07:01 +02:00

126 lines
4.4 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
use std::collections::BTreeMap;
use sylpheed_formats::PakArchive;
fn be32(b: &[u8], o: usize) -> u32 {
if o + 4 <= b.len() {
u32::from_be_bytes([b[o], b[o + 1], b[o + 2], b[o + 3]])
} else {
0
}
}
fn magic(b: &[u8]) -> String {
if b.len() < 4 {
return "(<4B)".into();
}
let m = &b[0..4];
if m.iter().all(|&c| (0x20..0x7f).contains(&c)) {
String::from_utf8_lossy(m).into()
} else if m == b"\x89PNG" {
"PNG".into()
} else if m == [0, 1, 0, 0] {
"ttf".into()
} else {
format!("{:02x}{:02x}{:02x}{:02x}", m[0], m[1], m[2], m[3])
}
}
fn main() {
let disc = std::env::var("SYLPHEED_DISC").unwrap();
// Known/understood IDXD schemas (semantic parsers we have)
let known_schema: BTreeMap<u32, &str> = [
(0x067025b9, "ADVERTISE_MOVIE (movie_manifest)"),
(0x13cb84ba, "sound registry / sounds.tbl"),
]
.into();
let mut fmt_count: BTreeMap<String, (u64, u64)> = BTreeMap::new(); // fmt -> (count, bytes)
let mut schema_census: BTreeMap<u32, (u64, u64, String)> = BTreeMap::new(); // schema -> (count,bytes,sample pak)
let mut unknown_magics: BTreeMap<String, (u64, Vec<String>)> = BTreeMap::new();
let paks: Vec<String> = {
let mut v = vec![];
for e in std::fs::read_dir(format!("{disc}/dat")).unwrap() {
let p = e.unwrap().path();
if p.extension().map(|x| x == "pak").unwrap_or(false) {
v.push(p.file_stem().unwrap().to_string_lossy().into());
}
}
v.sort();
v
};
println!("pak entries decompressed formats");
for pk in &paks {
let Ok(arc) = PakArchive::open(format!("{disc}/dat/{pk}.pak")) else {
continue;
};
let mut per: BTreeMap<String, u64> = BTreeMap::new();
let mut tot = 0u64;
let n = arc.entries().len();
for e in arc.entries() {
let Ok(b) = arc.read(e) else { continue };
tot += b.len() as u64;
let mut f = magic(&b);
if f == "IDXD" {
let s = be32(&b, 8);
schema_census.entry(s).or_insert((0, 0, pk.clone())).0 += 1;
schema_census.get_mut(&s).unwrap().1 += b.len() as u64;
f = format!("IDXD:{s:08x}");
} else if ![
"XPR2", "IXUD", "LSTA", "RATC", "RIFF", "XBG7", "OTTO", "PNG", "ttf", "DDS ",
"T8AD",
]
.contains(&f.as_str())
{
let ent = unknown_magics.entry(f.clone()).or_insert((0, vec![]));
ent.0 += 1;
if ent.1.len() < 3 && !ent.1.contains(pk) {
ent.1.push(pk.clone());
}
}
*per.entry(if f.starts_with("IDXD:") {
"IDXD".into()
} else {
f.clone()
})
.or_default() += 1;
let g = fmt_count
.entry(if f.starts_with("IDXD:") {
"IDXD".into()
} else {
f
})
.or_insert((0, 0));
g.0 += 1;
g.1 += b.len() as u64;
}
let mut fs: Vec<_> = per.into_iter().collect();
fs.sort_by_key(|x| std::cmp::Reverse(x.1));
let top: String = fs
.iter()
.take(4)
.map(|(k, v)| format!("{k}×{v}"))
.collect::<Vec<_>>()
.join(" ");
println!("{pk:26} {n:>7} {:>10}KB {top}", tot / 1024);
}
println!("\n=== FORMAT TOTALS (across all paks) ===");
let mut fv: Vec<_> = fmt_count.into_iter().collect();
fv.sort_by_key(|x| std::cmp::Reverse(x.1 .1));
for (f, (c, b)) in &fv {
println!(" {f:12} {c:>6} entries {:>8}KB", b / 1024);
}
println!(
"\n=== IDXD SCHEMA CENSUS ({} distinct schemas) ===",
schema_census.len()
);
let mut sv: Vec<_> = schema_census.into_iter().collect();
sv.sort_by_key(|x| std::cmp::Reverse(x.1 .1));
for (s, (c, b, pk)) in &sv {
let tag = known_schema.get(s).copied().unwrap_or("??? UNDECODED");
println!(
" {s:08x} {c:>5} ent {:>7}KB e.g. {pk:22} {tag}",
b / 1024
);
}
println!("\n=== UNKNOWN / UNCLASSIFIED MAGICS ===");
for (m, (c, pks)) in &unknown_magics {
println!(" {m:12} ×{c:<5} in {pks:?}");
}
}