Skip to content

feature: support latin1 characters for identifiers in spectra and chromatograms for mzML #47

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

Merged
mobiusklein merged 1 commit into from
Dec 1, 2025
Merged

feature: support latin1 characters for identifiers in spectra and chromatograms for mzML #47

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
1 change: 1 addition & 0 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.

3 changes: 2 additions & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ default = ["zlib-ng-compat", "mgf", "mzml"]
checksum = ["dep:md5", "dep:sha1", "dep:base16ct"]

mgf = []
mzml = ["dep:quick-xml", "checksum", "dep:memchr"]
mzml = ["dep:quick-xml", "checksum", "dep:memchr", "dep:encoding_rs"]
imzml = ["mzml", "dep:uuid"]

# mzsignal's main functionality requires a linear algebra backend.
Expand Down Expand Up @@ -201,6 +201,7 @@ pin-project-lite = { version = "0.2.16", optional = true }
memchr = { version = "2.7.4", optional = true }
libloading = { version = "0.8.6", optional = true }
zstd = { version = "0.13.3", optional = true }
encoding_rs = { version = "0.8.35", optional = true }


[dev-dependencies]
Expand Down
14 changes: 11 additions & 3 deletions src/io/mzml/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -738,7 +738,12 @@ impl<C: CentroidLike + BuildFromArrayMap, D: DeconvolutedCentroidLike + BuildFro
match attr_parsed {
Ok(attr) => match attr.key.as_ref() {
b"id" => {
self.entry_id = match attr.unescape_value() {
self.entry_id = match attr.unescape_value()
.map(|v| v.to_string())
.or_else(|_| -> Result<String, quick_xml::Error> {
log::warn!("Detected non-UTF8 character in spectrum id");
Ok(quick_xml::escape::escape(encoding_rs::mem::decode_latin1(&attr.value).as_ref()).into())
}) {
Ok(value) => value.to_string(),
Err(e) => {
return Err(xml_error!(
Expand Down Expand Up @@ -898,8 +903,11 @@ impl<C: CentroidLike + BuildFromArrayMap, D: DeconvolutedCentroidLike + BuildFro
b"id" => {
self.entry_id = attr
.unescape_value()
.expect("Error decoding id")
.to_string();
.map(|v| v.to_string())
.or_else(|_| -> Result<String, quick_xml::Error> {
log::warn!("Detected non-UTF8 character in chromatogram id");
Ok(quick_xml::escape::escape(encoding_rs::mem::decode_latin1(&attr.value).as_ref()).into())
}).unwrap();
trace!("Stored chromatogram id = {}", self.entry_id);
}
b"index" => {
Expand Down
10 changes: 8 additions & 2 deletions src/io/mzml/reading_shared.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,8 +461,14 @@ impl IndexedMzMLIndexExtractor {
if attr.key.as_ref() == b"idRef" {
self.last_id = attr
.unescape_value()
.expect("Error decoding idRef")
.to_string();
.map(|v| v.to_string())
.or_else(|_| -> Result<String, quick_xml::Error> {
log::warn!("Detected non-UTF8 character in idRef");
Ok(quick_xml::escape::escape(encoding_rs::mem::decode_latin1(&attr.value).as_ref()).into())
})
.unwrap_or_else(|e| {
panic!("Error decoding idRef on offset {e} from bytes {:?}", attr.value)
});
}
}
Err(err) => {
Expand Down
Loading