Skip to content

Rewrite readFeature to avoid using pattern matching #75

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

Open
Istar-Eldritch wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Rewrite readFeature to avoid using pattern matching #75

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
108 changes: 69 additions & 39 deletions src/main/java/uk/ac/ebi/embl/gff3tools/gff3/reader/GFF3FileReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ public GFF3FileReader(ValidationEngine validationEngine, Reader reader, Path gff
public GFF3Annotation readAnnotation() throws IOException, ValidationException {

String line;
GFF3Feature feature;
while ((line = readLine()) != null) {
if (line.isBlank()) {
// Ignore blank lines
Expand All @@ -91,10 +92,7 @@ public GFF3Annotation readAnnotation() throws IOException, ValidationException {
return previousAnnotation;
}
continue;
} else if ((m = GFF3_FEATURE.matcher(line)).matches()) {

GFF3Feature feature = readFeature(m);

} else if ((feature = readFeature(line)) != null) {
if (!feature.accession().equals(currentAccession)) {
// In case of different accession create a new GFF3Annotation and return the
// previous one.
Expand Down Expand Up @@ -202,42 +200,74 @@ private GFF3SequenceRegion readSequenceRegion(Matcher m) {
return new GFF3SequenceRegion(accessionId, accessionVersion, start, end);
}

private GFF3Feature readFeature(Matcher m) throws ValidationException {
private GFF3Feature readFeature(String line) throws ValidationException {

String accession = m.group("accession");
String accessionId = m.group("accessionId");
Optional<Integer> accessionVersion =
Optional.ofNullable(m.group("accessionVersion")).map(Integer::parseInt);
String source = m.group("source");
String name = m.group("name");
long start = Long.parseLong(m.group("start"));
long end = Long.parseLong(m.group("end"));
String score = m.group("score");
String strand = m.group("strand");
String phase = m.group("phase");
String attributes = m.group("attributes");

Map<String, Object> attributesMap = attributesFromString(attributes);

Optional<String> id = Optional.ofNullable((String) attributesMap.get("ID"));
Optional<String> parentId = Optional.ofNullable((String) attributesMap.get("Parent"));

GFF3Feature feature = new GFF3Feature(
id,
parentId,
accessionId,
accessionVersion,
source,
name,
start,
end,
score,
strand,
phase,
attributesMap);

validationEngine.validate(feature, lineCount);
return feature;
String[] parts = line.split("\t");
if (parts.length < 9) {
return null; // GFF2 features must have at least 9 fields
}
String accession = parts[0];
String source = parts[1];
String name = parts[2];
String start_str = parts[3];
String end_str = parts[4];
String score = parts[5];
String strand = parts[6];
String phase = parts[7];
String attributes = parts[8];

// Add additional checks as necessary
if (!accession.isEmpty()
&& !source.isEmpty()
&& !name.isEmpty()
&& (strand.equals("+") || strand.equals("-") || strand.equals(".") || strand.equals("?"))
&& isValidNumber(start_str)
&& isValidNumber(end_str)) {
Comment on lines +220 to +225
Copy link
Contributor

@Rajkumar-D Rajkumar-D Dec 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So this will silently ignore the lines that are not valid.
Better to log the ignored lines


String[] accessionParts = accession.split(".");

String accessionId = accessionParts.length > 0 ? accessionParts[0] : parts[0];
Optional<Integer> accessionVersion = Optional.ofNullable(
accessionParts.length > 1 ? accessionParts[0] : null)
.map(Integer::parseInt);

long start = Long.parseLong(parts[3]);
long end = Long.parseLong(parts[4]);

Map<String, Object> attributesMap = attributesFromString(attributes);

Optional<String> id = Optional.ofNullable((String) attributesMap.get("ID"));
Optional<String> parentId = Optional.ofNullable((String) attributesMap.get("Parent"));

GFF3Feature feature = new GFF3Feature(
id,
parentId,
accessionId,
accessionVersion,
source,
name,
start,
end,
score,
strand,
phase,
attributesMap);

validationEngine.validate(feature, lineCount);
return feature;
} else {
return null;
}
}

private boolean isValidNumber(String n) {
byte[] bytes = n.getBytes();
for (byte aByte : bytes) {
if (aByte < '0' || aByte > '9') {
return false;
}
}
return true;
}

private void validateAndSetSequenceRegion() throws ValidationException {
Expand Down