mirror of
https://github.com/bdbrown4/peltier.io.git
synced 2026-11-07 10:58:28 +00:00
Claude
4402775ed2
Attempt 4 (phase0-tokei-002, class 3, ACCEPTED — first auto-accept): every file was read through encoding_rs_io's DecodeReaderBytes via generic read_to_end, which zero-fills every grown buffer chunk (~221MB memset/run, 8.5% of Ir) and grows without a size hint. Patch: fs::read with a BOM-gated fallback to the identical decode path (a UTF-8-BOM file transcodes invalid sequences, so the fallback is required for equivalence). Gates: golden byte-identical; differential fuzz old-vs- new binaries 4,332 iterations (BOM grid, invalid UTF-8, binary junk, randomized) zero divergence; 250 upstream tests green; ASan+LSan clean with ASan-run output hashing to golden. Bench: +9.9% [8.0%, 12.7%]. Attempt 5 (phase0-tokei-003, ship tree, ACCEPTED): stacks fat LTO+cgu=1 (real +1.6% standalone but under threshold, phase0-tokei-001) on the accepted patch; benched as a whole vs pristine: +10.4% [8.5%, 12.0%]. Median clears the Phase 0 exit bar; CI lower bound 8.5%. Case study written (results/phase0/case-study-tokei.md), ledger at 5 attempts, CLAUDE.md phase line moved to Phase 1, next hypotheses logged (tokei class-5 byte-skip table; comrak class-3 arena). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
51 lines
1.9 KiB
Diff
51 lines
1.9 KiB
Diff
diff --git a/src/language/language_type.rs b/src/language/language_type.rs
|
|
index bffdf7a..86c9f94 100644
|
|
--- a/src/language/language_type.rs
|
|
+++ b/src/language/language_type.rs
|
|
@@ -1,6 +1,6 @@
|
|
use std::{
|
|
borrow::Cow,
|
|
- fmt,
|
|
+ fmt, fs,
|
|
fs::File,
|
|
io::{self, Read},
|
|
path::{Path, PathBuf},
|
|
@@ -38,17 +38,29 @@ impl LanguageType {
|
|
/// on success and giving back ownership of [`PathBuf`] on error.
|
|
pub fn parse(self, path: PathBuf, config: &Config) -> Result<Report, (io::Error, PathBuf)> {
|
|
let text = {
|
|
- let f = match File::open(&path) {
|
|
- Ok(f) => f,
|
|
+ // fs::read pre-sizes from metadata and skips buffer zeroing;
|
|
+ // the decoding reader only matters when a BOM is present, so
|
|
+ // BOM-less files (the overwhelming majority) take the raw path.
|
|
+ // encoding_rs_io passes BOM-less input through unchanged, so
|
|
+ // both paths produce identical bytes.
|
|
+ let raw = match fs::read(&path) {
|
|
+ Ok(raw) => raw,
|
|
Err(e) => return Err((e, path)),
|
|
};
|
|
- let mut s = Vec::new();
|
|
- let mut reader = DecodeReaderBytesBuilder::new().build(f);
|
|
-
|
|
- if let Err(e) = reader.read_to_end(&mut s) {
|
|
- return Err((e, path));
|
|
+ let has_bom = raw.starts_with(&[0xEF, 0xBB, 0xBF])
|
|
+ || raw.starts_with(&[0xFF, 0xFE])
|
|
+ || raw.starts_with(&[0xFE, 0xFF]);
|
|
+ if has_bom {
|
|
+ let mut s = Vec::new();
|
|
+ let mut reader =
|
|
+ DecodeReaderBytesBuilder::new().build(io::Cursor::new(raw));
|
|
+ if let Err(e) = reader.read_to_end(&mut s) {
|
|
+ return Err((e, path));
|
|
+ }
|
|
+ s
|
|
+ } else {
|
|
+ raw
|
|
}
|
|
- s
|
|
};
|
|
|
|
let mut stats = Report::new(path);
|