Skip to content

Write the entry identifier as a data item, not only as the block name #1144

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
josemduarte merged 1 commit into from
Aug 26, 2026
+60 −1
Merged

Write the entry identifier as a data item, not only as the block name #1144

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
21 changes: 20 additions & 1 deletion ...va-structure/src/main/java/org/biojava/nbio/structure/io/cif/AbstractCifFileSupplier.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,8 +40,27 @@ protected CifFile getInternal(Structure structure, List<WrappedAtom> wrappedAtom
// entity information
List<EntityInfo> entityInfos = structure.getEntityInfos();

PdbId pdbId = structure.getPdbId();

MmCifBlockBuilder blockBuilder = CifBuilder.enterFile(StandardSchemata.MMCIF)
.enterBlock(structure.getPdbId() == null? "" : structure.getPdbId().getId());
.enterBlock(pdbId == null? "" : pdbId.getId());

if (pdbId != null) {
// The block header alone does not carry the identifier for consumers: readers pick it up from
// _entry.id (e.g. Jmol) or from _struct.entry_id (BioJava's own CifStructureConsumerImpl).
// Both are written so that the identifier survives a write-then-read round trip either way.
blockBuilder.enterEntry()
.enterId()
.add(pdbId.getId())
.leaveColumn()
.leaveCategory();

blockBuilder.enterStruct()
.enterEntryId()
.add(pdbId.getId())
.leaveColumn()
.leaveCategory();
}

blockBuilder.enterStructKeywords().enterText()
.add(String.join(", ", structure.getPDBHeader().getKeywords()))
Expand Down
40 changes: 40 additions & 0 deletions ...va-structure/src/test/java/org/biojava/nbio/structure/io/cif/CifFileSupplierImplTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
package org.biojava.nbio.structure.io.cif;

import org.biojava.nbio.structure.PdbId;
import org.biojava.nbio.structure.Structure;
import org.biojava.nbio.structure.io.FileParsingParameters;
import org.biojava.nbio.structure.io.PDBFileParser;
Expand Down Expand Up @@ -41,4 +42,43 @@ public void shouldReadRawPdbOutputtingCifWithEntity() throws IOException {
}

}

/**
* The identifier must be written as a data item and not only as the name of the data block: consumers read it
* from _entry.id or from _struct.entry_id, so writing the block header alone loses it. See issue #1143.
*/
@Test
public void shouldWriteEntryIdAndSurviveRoundTrip() throws IOException {
Structure s;
try (InputStream inStream = new GZIPInputStream(this.getClass().getResourceAsStream("/4hhb.cif.gz"))) {
s = CifStructureConverter.fromInputStream(inStream);
}
assertEquals(new PdbId("4HHB"), s.getPdbId());

String cifText = CifStructureConverter.toText(s);
assertTrue("_entry.id must be written", cifText.contains("_entry.id"));
assertTrue("_struct.entry_id must be written", cifText.contains("_struct.entry_id"));

Structure readStruct = CifStructureConverter.fromInputStream(
new ByteArrayInputStream(cifText.getBytes()));

assertEquals(s.getPdbId(), readStruct.getPdbId());
assertEquals(s.getPdbId(), readStruct.getPDBHeader().getPdbId());
}

/**
* Structures without an identifier must not gain empty entry categories.
*/
@Test
public void shouldNotWriteEntryIdWhenPdbIdIsAbsent() throws IOException {
Structure s;
try (InputStream inStream = new GZIPInputStream(this.getClass().getResourceAsStream("/4hhb.cif.gz"))) {
s = CifStructureConverter.fromInputStream(inStream);
}
s.setPdbId(null);

String cifText = CifStructureConverter.toText(s);
assertFalse(cifText.contains("_entry.id"));
assertFalse(cifText.contains("_struct.entry_id"));
}
}
Loading