Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(file source): fix regression in fingerprint calculations #8187

Closed
wants to merge 1 commit into from
Closed

fix(file source): fix regression in fingerprint calculations #8187

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion lib/file-source/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ libc = "0.2"
winapi = { version = "0.3", features = ["winioctl"] }

[dependencies]
crc = "2.0.0"
crc = "1.8.1"
glob = "0.3.0"
scan_fmt = "0.2.6"

Expand Down
31 changes: 19 additions & 12 deletions lib/file-source/src/fingerprinter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
use crate::{metadata_ext::PortableFileExt, FileSourceInternalEvents};
use crc::Crc;
use serde::{Deserialize, Serialize};
use std::{
collections::HashSet,
Expand All @@ -9,8 +8,6 @@ use std::{
};
use tracing::trace_span;

const FINGERPRINT_CRC: Crc<u64> = Crc::<u64>::new(&crc::CRC_64_ECMA_182);

#[derive(Clone)]
pub struct Fingerprinter {
pub strategy: FingerprintStrategy,
Expand All @@ -37,6 +34,7 @@ pub enum FingerprintStrategy {
pub enum FileFingerprint {
#[serde(rename = "checksum")]
BytesChecksum(u64),
#[serde(alias = "first_line_checksum")]
FirstLinesChecksum(u64),
DevInode(u64, u64),
Unknown(u64),
Expand All @@ -53,7 +51,7 @@ impl FileFingerprint {
let mut buf = Vec::with_capacity(std::mem::size_of_val(dev) * 2);
buf.write_all(&dev.to_be_bytes()).expect("writing to array");
buf.write_all(&ino.to_be_bytes()).expect("writing to array");
FINGERPRINT_CRC.checksum(&buf[..])
crc::crc64::checksum_ecma(&buf[..])
}
Unknown(c) => *c,
}
Expand Down Expand Up @@ -94,7 +92,7 @@ impl Fingerprinter {
let mut fp = fs::File::open(path)?;
fp.seek(SeekFrom::Start(ignored_header_bytes as u64))?;
fingerprinter_read_until(fp, b'\n', lines, buffer)?;
let fingerprint = FINGERPRINT_CRC.checksum(&buffer[..]);
let fingerprint = crc::crc64::checksum_ecma(&buffer[..]);
Ok(FirstLinesChecksum(fingerprint))
}
}
Expand Down Expand Up @@ -151,7 +149,7 @@ impl Fingerprinter {
let mut fp = fs::File::open(path)?;
fp.seek(io::SeekFrom::Start(ignored_header_bytes as u64))?;
fp.read_exact(&mut buffer[..bytes])?;
let fingerprint = FINGERPRINT_CRC.checksum(&buffer[..]);
let fingerprint = crc::crc64::checksum_ecma(&buffer[..]);
Ok(Some(FileFingerprint::BytesChecksum(fingerprint)))
}
_ => Ok(None),
Expand Down Expand Up @@ -193,7 +191,7 @@ fn fingerprinter_read_until(

#[cfg(test)]
mod test {
use super::{FileSourceInternalEvents, FingerprintStrategy, Fingerprinter};
use super::{FileFingerprint, FileSourceInternalEvents, FingerprintStrategy, Fingerprinter};
use std::{collections::HashSet, fs, io::Error, path::Path, time::Duration};
use tempfile::tempdir;

Expand Down Expand Up @@ -226,9 +224,12 @@ mod test {
assert!(fingerprinter
.get_fingerprint_of_file(&empty_path, &mut buf)
.is_err());
assert!(fingerprinter
.get_fingerprint_of_file(&full_line_path, &mut buf)
.is_ok());
assert_eq!(
fingerprinter
.get_fingerprint_of_file(&full_line_path, &mut buf)
.unwrap(),
FileFingerprint::FirstLinesChecksum(8302183670541403209),
);
assert!(fingerprinter
.get_fingerprint_of_file(&not_full_line_path, &mut buf)
.is_err());
Expand Down Expand Up @@ -298,7 +299,10 @@ mod test {
assert!(run(&incomlete_line).is_err());
assert!(run(&incomplete_under_max_line_length_by_one).is_err());

assert!(run(&one_line).is_ok());
assert_eq!(
run(&one_line).unwrap(),
FileFingerprint::FirstLinesChecksum(12790833211255586118)
);
assert!(run(&one_line_duplicate).is_ok());
assert!(run(&one_line_continued).is_ok());
assert!(run(&different_two_lines).is_ok());
Expand Down Expand Up @@ -356,7 +360,10 @@ mod test {

assert!(run(&incomlete_lines).is_err());

assert!(run(&two_lines).is_ok());
assert_eq!(
run(&two_lines).unwrap(),
FileFingerprint::FirstLinesChecksum(8288549968916239272)
);
assert!(run(&two_lines_duplicate).is_ok());
assert!(run(&two_lines_continued).is_ok());
assert!(run(&different_three_lines).is_ok());
Expand Down