@@ -155,6 +155,11 @@ CC(=O)OC(CC(=O)[O-])C[N+](C)(C)C > <PUBCHEM_BONDANNOTATIONS> 7 6 3 +> <MULTILINE_DATA> +line1 +line2 +line3 + $$$$ 2 -OEChem-07120805312D resources/pubchem_sample_33.sdf @@ -118,14 +118,14 @@ public class SDFileReader if (pattern == null) { - pattern = Pattern.compile(".*^> *?<" + key + ">$.(.*?)$.*", Pattern.MULTILINE | Pattern.DOTALL); + pattern = Pattern.compile(".*^> *?<" + key + ">$(.*?)$^$.*", Pattern.MULTILINE | Pattern.DOTALL); keyPatterns.put(key, pattern); } Matcher matcher = pattern.matcher(record); - return matcher.matches() ? matcher.group(1) : ""; + return matcher.matches() ? matcher.group(1).trim() : ""; } public Molecule getMolecule() src/com/metamolecular/mx/io/mdl/SDFileReader.java @@ -40,7 +40,7 @@ public class SDFileReaderTest extends TestCase private SDFileReader reader; private String[] keys = { - "PUBCHEM_COMPOUND_CID", "PUBCHEM_COMPOUND_CANONICALIZED", "PUBCHEM_CACTVS_COMPLEXITY", "PUBCHEM_CACTVS_HBOND_ACCEPTOR", "PUBCHEM_CACTVS_HBOND_DONOR", "PUBCHEM_CACTVS_ROTATABLE_BOND", "PUBCHEM_CACTVS_SUBSKEYS", "PUBCHEM_IUPAC_OPENEYE_NAME", "PUBCHEM_IUPAC_CAS_NAME", "PUBCHEM_IUPAC_NAME", "PUBCHEM_IUPAC_SYSTEMATIC_NAME", "PUBCHEM_IUPAC_TRADITIONAL_NAME", "PUBCHEM_NIST_INCHI", "PUBCHEM_EXACT_MASS", "PUBCHEM_MOLECULAR_FORMULA", "PUBCHEM_MOLECULAR_WEIGHT", "PUBCHEM_OPENEYE_CAN_SMILES", "PUBCHEM_OPENEYE_ISO_SMILES", "PUBCHEM_CACTVS_TPSA", "PUBCHEM_MONOISOTOPIC_WEIGHT", "PUBCHEM_TOTAL_CHARGE", "PUBCHEM_HEAVY_ATOM_COUNT", "PUBCHEM_ATOM_DEF_STEREO_COUNT", "PUBCHEM_ATOM_UDEF_STEREO_COUNT", "PUBCHEM_BOND_DEF_STEREO_COUNT", "PUBCHEM_BOND_UDEF_STEREO_COUNT", "PUBCHEM_ISOTOPIC_ATOM_COUNT", "PUBCHEM_COMPONENT_COUNT", "PUBCHEM_CACTVS_TAUTO_COUNT", "PUBCHEM_BONDANNOTATIONS" + "PUBCHEM_COMPOUND_CID", "PUBCHEM_COMPOUND_CANONICALIZED", "PUBCHEM_CACTVS_COMPLEXITY", "PUBCHEM_CACTVS_HBOND_ACCEPTOR", "PUBCHEM_CACTVS_HBOND_DONOR", "PUBCHEM_CACTVS_ROTATABLE_BOND", "PUBCHEM_CACTVS_SUBSKEYS", "PUBCHEM_IUPAC_OPENEYE_NAME", "PUBCHEM_IUPAC_CAS_NAME", "PUBCHEM_IUPAC_NAME", "PUBCHEM_IUPAC_SYSTEMATIC_NAME", "PUBCHEM_IUPAC_TRADITIONAL_NAME", "PUBCHEM_NIST_INCHI", "PUBCHEM_EXACT_MASS", "PUBCHEM_MOLECULAR_FORMULA", "PUBCHEM_MOLECULAR_WEIGHT", "PUBCHEM_OPENEYE_CAN_SMILES", "PUBCHEM_OPENEYE_ISO_SMILES", "PUBCHEM_CACTVS_TPSA", "PUBCHEM_MONOISOTOPIC_WEIGHT", "PUBCHEM_TOTAL_CHARGE", "PUBCHEM_HEAVY_ATOM_COUNT", "PUBCHEM_ATOM_DEF_STEREO_COUNT", "PUBCHEM_ATOM_UDEF_STEREO_COUNT", "PUBCHEM_BOND_DEF_STEREO_COUNT", "PUBCHEM_BOND_UDEF_STEREO_COUNT", "PUBCHEM_ISOTOPIC_ATOM_COUNT", "PUBCHEM_COMPONENT_COUNT", "PUBCHEM_CACTVS_TAUTO_COUNT", "PUBCHEM_BONDANNOTATIONS", "MULTILINE_DATA" }; @Override @@ -160,4 +160,13 @@ public class SDFileReaderTest extends TestCase assertFalse(molecule.countAtoms() == 0); } } + + public void testItShouldReadAMultilineField() + { + reader.nextRecord(); + + String multiline = reader.getData("MULTILINE_DATA"); + + assertEquals("line1\nline2\nline3", multiline); + } } src/com/metamolecular/mx/test/SDFileReaderTest.java 7a1acdbc239fd37fbef14cafbe0de2066124d390 Richard Apodaca rapodaca@metamolecular.com http://github.com/rapodaca/mx/commit/850e33a44b719381c33b422263a08a1a172d0fcf 850e33a44b719381c33b422263a08a1a172d0fcf 2009-01-05T21:34:09-08:00 2009-01-05T21:34:09-08:00 test/impl of reading multiline data in sd file b0b4129c8f889503004458b52c6ed390ae9f5cb8 Richard Apodaca rapodaca@metamolecular.com