Skip to content

CONECT/LINK line-length bug fix for the PDB Parser (already in BioJava Master branch). #707

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 2 commits into from
Oct 19, 2017
Merged

CONECT/LINK line-length bug fix for the PDB Parser (already in BioJava Master branch). #707

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
50c34d3
Added exception handler for out-of-bounds errors when parsing lines, …
Nov 30, 2016
e88637c
Changes for CONECT/LINK
larsonmattr Oct 18, 2017
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
115 changes: 64 additions & 51 deletions biojava-structure/src/main/java/org/biojava/nbio/structure/io/PDBFileParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2017,6 +2017,8 @@ private void switchCAOnly(){

/** safes repeating a few lines ... */
private Integer conect_helper (String line,int start,int end) {
if (line.length() < end) return null;

String sbond = line.substring(start,end).trim();
int bond = -1 ;
Integer b = null ;
Expand Down Expand Up @@ -2343,7 +2345,15 @@ private void pdb_SSBOND_Handler(String line){
private void pdb_LINK_Handler(String line) {

if (params.isHeaderOnly()) return;

// Check for the minimal set of fields.
if (line.length()<56) {
logger.info("LINK line has length under 56. Ignoring it.");
return;
}

int len = line.length();

String name1 = line.substring(12, 16).trim();
String altLoc1 = line.substring(16, 17).trim();
String resName1 = line.substring(17, 20).trim();
Expand All @@ -2356,10 +2366,13 @@ private void pdb_LINK_Handler(String line) {
String resName2 = line.substring(47, 50).trim();
String chainID2 = line.substring(51, 52).trim();
String resSeq2 = line.substring(52, 56).trim();
String iCode2 = line.substring(56, 57).trim();
String iCode2 = null; // Might get trimmed if blank.
if (len > 56) iCode2 = line.substring(56, 57).trim();

String sym1 = line.substring(59, 65).trim();
String sym2 = line.substring(66, 72).trim();
String sym1 = null;
if (len > 64) sym1 = line.substring(59, 65).trim();
String sym2 = null;
if (len > 71) sym2 = line.substring(66, 72).trim();

// System.err.println("LINK");
// System.err.println("\tName: " + name1);
Expand Down Expand Up @@ -2690,54 +2703,54 @@ public Structure parsePDBFile(BufferedReader buf)

String recordName = line.substring (0, 6).trim ();

if (recordName.equals("ATOM"))
pdb_ATOM_Handler(line);
else if (recordName.equals("SEQRES"))
pdb_SEQRES_Handler(line);
else if (recordName.equals("HETATM"))
pdb_ATOM_Handler(line);
else if (recordName.equals("MODEL"))
pdb_MODEL_Handler(line);
else if (recordName.equals("HEADER"))
pdb_HEADER_Handler(line);
else if (recordName.equals("AUTHOR"))
pdb_AUTHOR_Handler(line);
else if (recordName.equals("TITLE"))
pdb_TITLE_Handler(line);
else if (recordName.equals("SOURCE"))
sourceLines.add(line); //pdb_SOURCE_Handler
else if (recordName.equals("COMPND"))
compndLines.add(line); //pdb_COMPND_Handler
else if (recordName.equals("JRNL"))
pdb_JRNL_Handler(line);
else if (recordName.equals("EXPDTA"))
pdb_EXPDTA_Handler(line);
else if (recordName.equals("CRYST1"))
pdb_CRYST1_Handler(line);
else if (recordName.startsWith("MTRIX"))
pdb_MTRIXn_Handler(line);
else if (recordName.equals("REMARK"))
pdb_REMARK_Handler(line);
else if (recordName.equals("CONECT"))
pdb_CONECT_Handler(line);
else if (recordName.equals("REVDAT"))
pdb_REVDAT_Handler(line);
else if (recordName.equals("DBREF"))
pdb_DBREF_Handler(line);
else if (recordName.equals("SITE"))
pdb_SITE_Handler(line);
else if (recordName.equals("SSBOND"))
pdb_SSBOND_Handler(line);
else if (recordName.equals("LINK"))
pdb_LINK_Handler(line);
else if ( params.isParseSecStruc()) {
if ( recordName.equals("HELIX") ) pdb_HELIX_Handler ( line ) ;
else if (recordName.equals("SHEET")) pdb_SHEET_Handler(line ) ;
else if (recordName.equals("TURN")) pdb_TURN_Handler( line ) ;
}
else {
// this line type is not supported, yet.
// we ignore it
try {
if (recordName.equals("ATOM"))
pdb_ATOM_Handler(line);
else if (recordName.equals("SEQRES"))
pdb_SEQRES_Handler(line);
else if (recordName.equals("HETATM"))
pdb_ATOM_Handler(line);
else if (recordName.equals("MODEL"))
pdb_MODEL_Handler(line);
else if (recordName.equals("HEADER"))
pdb_HEADER_Handler(line);
else if (recordName.equals("AUTHOR"))
pdb_AUTHOR_Handler(line);
else if (recordName.equals("TITLE"))
pdb_TITLE_Handler(line);
else if (recordName.equals("SOURCE"))
sourceLines.add(line); //pdb_SOURCE_Handler
else if (recordName.equals("COMPND"))
compndLines.add(line); //pdb_COMPND_Handler
else if (recordName.equals("JRNL"))
pdb_JRNL_Handler(line);
else if (recordName.equals("EXPDTA"))
pdb_EXPDTA_Handler(line);
else if (recordName.equals("CRYST1"))
pdb_CRYST1_Handler(line);
else if (recordName.startsWith("MTRIX"))
pdb_MTRIXn_Handler(line);
else if (recordName.equals("REMARK"))
pdb_REMARK_Handler(line);
else if (recordName.equals("CONECT"))
pdb_CONECT_Handler(line);
else if (recordName.equals("REVDAT"))
pdb_REVDAT_Handler(line);
else if (recordName.equals("DBREF"))
pdb_DBREF_Handler(line);
else if (recordName.equals("SITE"))
pdb_SITE_Handler(line);
else if (recordName.equals("SSBOND"))
pdb_SSBOND_Handler(line);
else if (recordName.equals("LINK"))
pdb_LINK_Handler(line);
else if ( params.isParseSecStruc()) {
if ( recordName.equals("HELIX") ) pdb_HELIX_Handler ( line ) ;
else if (recordName.equals("SHEET")) pdb_SHEET_Handler(line ) ;
else if (recordName.equals("TURN")) pdb_TURN_Handler( line ) ;
}
} catch (StringIndexOutOfBoundsException ex) {
logger.info("Unable to parse [" + line + "]");
Copy link
Copy Markdown
Contributor

@josemduarte josemduarte Sep 12, 2017

Choose a reason for hiding this comment

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

This should be warn level

}


Expand Down
74 changes: 74 additions & 0 deletions biojava-structure/src/test/java/org/biojava/nbio/structure/io/TestShortLines.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,74 @@
package org.biojava.nbio.structure.io;

import static org.junit.Assert.assertEquals;

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.biojava.nbio.structure.Atom;
import org.biojava.nbio.structure.Chain;
import org.biojava.nbio.structure.Group;
import org.biojava.nbio.structure.Structure;
import org.junit.Test;

/**
* This class will test parsing short CONECT lines.
* <p>(c) 2016 DNASTAR, Inc.</p>
Copy link
Copy Markdown
Contributor

@josemduarte josemduarte Sep 12, 2017

Choose a reason for hiding this comment

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

Please remove this for biojava code

* @since Nov 30, 2016
* @author larsonm
*/
public class TestShortLines {

@Test
public void testConect() throws IOException {
PDBFileParser pdbPars = new PDBFileParser();
FileParsingParameters params = pdbPars.getFileParsingParameters();
params.setCreateAtomBonds(true);

// CONECTS will be deprecated, but will we create bonds?
// Like the LINK records, should BioJava create BondImpl when params.setCreateAtomBonds(true)?

StringBuilder sb = new StringBuilder();
sb.append("HETATM 2398 P FAD A 500 8.398 46.448 73.490 1.00 13.51 P \n");
sb.append("HETATM 2399 PA FAD A 500 6.089 45.580 75.235 1.00 15.88 P \n");
sb.append("HETATM 2400 O1P FAD A 500 7.908 47.684 72.869 1.00 4.19 O \n");
sb.append("CONECT 2400 2398\n");
String shortLine = sb.toString();
Structure s;
// Parse short
try(InputStream is = new ByteArrayInputStream(shortLine.getBytes())) {
s = pdbPars.parsePDBFile(is);
}

// After 4.2, CONECTS are deprecated, but there is not yet an implementation
// describing how CONECTS will be replaced - will Bonds be created?
assertEquals(1, s.getConnections().size());
}

@Test
public void testLINK() throws IOException {
Structure s;
PDBFileParser pdbPars = new PDBFileParser();
FileParsingParameters params = pdbPars.getFileParsingParameters();
params.setCreateAtomBonds(true);

StringBuilder sb = new StringBuilder();
sb.append("ATOM 2412 C21 2EG A 7 0.888 44.973 72.238 1.00 29.17 C \n");
sb.append("ATOM 2413 C22 2EG B 19 0.888 44.973 72.238 1.00 29.17 C \n");
//sb.append("LINK C21 2EG A 7 C22 2EG B 19 1555 1555 1.56 ");
sb.append("LINK C21 2EG A 7 C22 2EG B 19\n");
String shortLine = sb.toString();

// Parse short
try(InputStream is = new ByteArrayInputStream(shortLine.getBytes())) {
s = pdbPars.parsePDBFile(is);
}

// Should be a bond present in the Atoms.
Chain c = s.getChain(0, 0);
Group g = c.getAtomGroups().get(0);
Atom a = g.getAtom(0);
assertEquals(1, a.getBonds().size());
}
}