label.set_this_label_text = set this label text
label.sequences_from = Sequences from {0}
label.successfully_loaded_file = Successfully loaded file {0}
+label.successfully_loaded_matrix = Successfully loaded score matrix {0}
label.successfully_saved_to_file_in_format = Successfully saved to file: {0} in {1} format.
label.copied_sequences_to_clipboard = Copied {0} sequences to clipboard.
label.check_file_matches_sequence_ids_alignment = Check that the file matches sequence IDs in the alignment.
import jalview.api.analysis.ScoreModelI;
-import java.io.BufferedReader;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
import java.util.Arrays;
-import java.util.StringTokenizer;
public class ScoreMatrix extends PairwiseSeqScoreModel implements
ScoreModelI
{
public static final short UNMAPPED = (short) -1;
- private static final String DELIMITERS = " ,\t";
-
- private static final String COMMENT_CHAR = "#";
-
private static final String BAD_ASCII_ERROR = "Unexpected character %s in getPairwiseScore";
private static final int MAX_ASCII = 127;
}
return sb.toString();
}
-
- /**
- * Parse a score matrix from the given input stream and returns a ScoreMatrix
- * object. If parsing fails, error messages are written to syserr and null is
- * returned. It is the caller's responsibility to close the input stream.
- * Expected format:
- *
- * <pre>
- * ScoreMatrix displayName
- * # comment lines begin with hash sign
- * # symbol alphabet should be the next non-comment line
- * ARNDCQEGHILKMFPSTWYVBZX *
- * # scores matrix, with space, comma or tab delimited values
- * # [i, j] = score for substituting symbol[i] with symbol[j]
- * # first column in each row is optionally the 'substituted' symbol
- * A 4 -1 -2 -2 0 -1 -1 0 -2 -1 -1 -1 -1 -2 -1 1 0 -3 -2 0 -2 -1 0 -4 -4
- * ..etc..
- * </pre>
- *
- * @param is
- * @return
- */
- public static ScoreMatrix parse(InputStream is)
- {
- ScoreMatrix sm = null;
- BufferedReader br = new BufferedReader(new InputStreamReader(is));
- int lineNo = 0;
- String name = null;
- String alphabet = null;
- float[][] scores = null;
- int size = 0;
- int row = 0;
-
- try
- {
- String data;
-
- while ((data = br.readLine()) != null)
- {
- lineNo++;
- data = data.trim();
- if (data.startsWith(COMMENT_CHAR))
- {
- continue;
- }
- if (data.toLowerCase().startsWith("scorematrix"))
- {
- /*
- * Parse name from ScoreMatrix <name>
- */
- if (name != null)
- {
- System.err
- .println("Warning: 'ScoreMatrix' repeated in file at line "
- + lineNo);
- }
- StringTokenizer nameLine = new StringTokenizer(data, DELIMITERS);
- if (nameLine.countTokens() != 2)
- {
- System.err
- .println("Format error: expected 'ScoreMatrix <name>', found '"
- + data + "' at line " + lineNo);
- return null;
- }
- nameLine.nextToken();
- name = nameLine.nextToken();
- continue;
- }
- else if (name == null)
- {
- System.err
- .println("Format error: 'ScoreMatrix <name>' should be the first non-comment line");
- return null;
- }
-
- /*
- * next line after ScoreMatrix should be the alphabet of scored symbols
- */
- if (alphabet == null)
- {
- alphabet = data;
- size = alphabet.length();
- scores = new float[size][];
- continue;
- }
-
- /*
- * too much information?
- */
- if (row >= size && data.length() > 0) {
- System.err
- .println("Unexpected extra input line in score model file "
- + data);
- return null;
- }
-
- /*
- * subsequent lines should be the symbol scores
- * optionally with the symbol as the first column for readability
- */
- StringTokenizer scoreLine = new StringTokenizer(data, DELIMITERS);
- if (scoreLine.countTokens() == size + 1)
- {
- /*
- * check 'guide' symbol is the row'th letter of the alphabet
- */
- String symbol = scoreLine.nextToken();
- if (symbol.length() > 1
- || symbol.charAt(0) != alphabet.charAt(row))
- {
- System.err
- .println(String
- .format("Error parsing score matrix at line %d, expected %s but found %s",
- lineNo, alphabet.charAt(row), symbol));
- return null;
- }
- }
- if (scoreLine.countTokens() != size)
- {
- System.err.println(String.format(
- "Expected %d scores at line %d but found %d", size,
- lineNo, scoreLine.countTokens()));
- return null;
- }
- scores[row] = new float[size];
- int col = 0;
- String value = null;
- while (scoreLine.hasMoreTokens())
- {
- try
- {
- value = scoreLine.nextToken();
- scores[row][col] = Float.valueOf(value);
- col++;
- } catch (NumberFormatException e)
- {
- System.err.println(String.format(
- "Invalid score value %s at line %d column %d", value,
- lineNo, col));
- return null;
- }
- }
- row++;
- }
- } catch (IOException e)
- {
- System.err.println("Error reading score matrix file: "
- + e.getMessage() + " at line " + lineNo);
- }
-
- /*
- * out of data - check we found enough
- */
- if (row < size)
- {
- System.err
- .println(String
- .format("Expected %d rows of score data in score matrix but only found %d",
- size, row));
- return null;
- }
-
- /*
- * If we get here, then name, alphabet and scores have been parsed successfully
- */
- sm = new ScoreMatrix(name, alphabet.toCharArray(), scores);
- return sm;
- }
}
package jalview.analysis.scoremodels;
import jalview.api.analysis.ScoreModelI;
+import jalview.io.DataSourceType;
+import jalview.io.FileParse;
+import jalview.io.ScoreMatrixFile;
import java.io.IOException;
-import java.io.InputStream;
-import java.net.URL;
import java.util.Map;
import java.util.TreeMap;
* using TreeMap keeps models ordered alphabetically by name
*/
models = new TreeMap<String, ScoreModelI>(String.CASE_INSENSITIVE_ORDER);
- loadScoreMatrix("/scoreModel/blosum62.scm");
- loadScoreMatrix("/scoreModel/pam250.scm");
- loadScoreMatrix("/scoreModel/dna.scm");
+ loadScoreMatrix("scoreModel/blosum62.scm");
+ loadScoreMatrix("scoreModel/pam250.scm");
+ loadScoreMatrix("scoreModel/dna.scm");
registerScoreModel(new FeatureScoreModel());
registerScoreModel(new PIDScoreModel());
}
/**
* Try to load a score matrix from the given resource file, and if successful,
- * register it. Answers true if successful, else false. Any errors are
- * reported on syserr but not thrown.
+ * register it. Answers true if successful, else false.
*
* @param string
*/
boolean loadScoreMatrix(String resourcePath)
{
- URL url = this.getClass().getResource(resourcePath);
- if (url == null)
- {
- System.err.println("Failed to locate " + resourcePath);
- return false;
- }
- boolean success = false;
- InputStream is = null;
try
{
- is = url.openStream();
- ScoreMatrix sm = ScoreMatrix.parse(is);
- if (sm != null)
- {
- registerScoreModel(sm);
- success = true;
- }
+ /*
+ * delegate parsing to ScoreMatrixFile
+ */
+ FileParse fp = new FileParse(resourcePath, DataSourceType.CLASSLOADER);
+ ScoreMatrix sm = new ScoreMatrixFile(fp).parseMatrix();
+ registerScoreModel(sm);
+ return true;
} catch (IOException e)
{
- } finally
- {
- if (is != null)
- {
- try
- {
- is.close();
- } catch (IOException e)
- {
- }
- }
+ System.err.println("Error reading " + resourcePath + ": "
+ + e.getMessage());
}
- return success;
+ return false;
}
/**
import jalview.io.FileFormatI;
import jalview.io.FileFormats;
import jalview.io.FileLoader;
+import jalview.io.FileParse;
import jalview.io.FormatAdapter;
import jalview.io.HtmlSvgOutput;
import jalview.io.IdentifyFile;
import jalview.io.JalviewFileView;
import jalview.io.JnetAnnotationMaker;
import jalview.io.NewickFile;
+import jalview.io.ScoreMatrixFile;
import jalview.io.TCoffeeScoreFile;
import jalview.jbgui.GAlignFrame;
import jalview.schemes.ColourSchemeI;
}
/**
- * Attempt to load a "dropped" file or URL string: First by testing whether
- * it's an Annotation file, then a JNet file, and finally a features file. If
- * all are false then the user may have dropped an alignment file onto this
- * AlignFrame.
+ * Attempt to load a "dropped" file or URL string, by testing in turn for
+ * <ul>
+ * <li>an Annotation file</li>
+ * <li>a JNet file</li>
+ * <li>a features file</li>
+ * <li>else try to interpret as an alignment file</li>
+ * </ul>
*
* @param file
* either a filename or a URL string.
{
format = new IdentifyFile().identify(file, sourceType);
}
- if (FileFormat.Jnet.equals(format))
+ if (FileFormat.ScoreMatrix == format)
+ {
+ ScoreMatrixFile sm = new ScoreMatrixFile(new FileParse(file,
+ sourceType));
+ sm.parse();
+ // todo: i18n this message
+ statusBar
+ .setText(MessageManager.formatMessage(
+ "label.successfully_loaded_matrix",
+ sm.getMatrixName()));
+ }
+ else if (FileFormat.Jnet.equals(format))
{
JPredFile predictions = new JPredFile(file, sourceType);
new JnetAnnotationMaker();
return new FeaturesFile();
}
},
+ ScoreMatrix("Substitution matrix", "", false, false)
+ {
+ @Override
+ public AlignmentFileReaderI getReader(FileParse source)
+ throws IOException
+ {
+ return new ScoreMatrixFile(source);
+ }
+
+ @Override
+ public AlignmentFileWriterI getWriter(AlignmentI al)
+ {
+ return null;
+ }
+ },
PDB("PDB", "pdb,ent", true, false)
{
@Override
}
data = data.toUpperCase();
+ if (data.startsWith(ScoreMatrixFile.SCOREMATRIX))
+ {
+ reply = FileFormat.ScoreMatrix;
+ break;
+ }
if (data.startsWith("##GFF-VERSION"))
{
// GFF - possibly embedded in a Jalview features file!
--- /dev/null
+package jalview.io;
+
+import jalview.analysis.scoremodels.ScoreMatrix;
+import jalview.analysis.scoremodels.ScoreModels;
+import jalview.datamodel.SequenceI;
+
+import java.io.IOException;
+import java.util.StringTokenizer;
+
+/**
+ * A class that can parse a file containing a substitution matrix and register
+ * it for use in Jalview
+ *
+ * @author gmcarstairs
+ *
+ */
+// TODO modify the AlignFile / IdentifyFile pattern so that non-alignment files
+// like this are handled more naturally
+public class ScoreMatrixFile extends AlignFile implements
+ AlignmentFileReaderI
+{
+ // first non-comment line identifier - also checked in IdentifyFile
+ public static final String SCOREMATRIX = "SCOREMATRIX";
+
+ private static final String DELIMITERS = " ,\t";
+
+ private static final String COMMENT_CHAR = "#";
+
+ private String matrixName;
+
+ /**
+ * Constructor
+ *
+ * @param source
+ * @throws IOException
+ */
+ public ScoreMatrixFile(FileParse source) throws IOException
+ {
+ super(false, source);
+ }
+
+ @Override
+ public String print(SequenceI[] sqs, boolean jvsuffix)
+ {
+ return null;
+ }
+
+ /**
+ * Parses the score matrix file, and if successful registers the matrix so it
+ * will be shown in Jalview menus.
+ */
+ @Override
+ public void parse() throws IOException
+ {
+ ScoreMatrix sm = parseMatrix();
+
+ ScoreModels.getInstance().registerScoreModel(sm);
+ }
+
+ /**
+ * Parses the score matrix file and constructs a ScoreMatrix object. If an
+ * error is found in parsing, it is thrown as FileFormatException. Any
+ * warnings are written to syserr.
+ *
+ * @return
+ * @throws IOException
+ */
+ public ScoreMatrix parseMatrix() throws IOException
+ {
+ ScoreMatrix sm = null;
+ int lineNo = 0;
+ String name = null;
+ String alphabet = null;
+ float[][] scores = null;
+ int size = 0;
+ int row = 0;
+ String err = null;
+ String data;
+
+ while ((data = nextLine()) != null)
+ {
+ lineNo++;
+ data = data.trim();
+ if (data.startsWith(COMMENT_CHAR) || data.length() == 0)
+ {
+ continue;
+ }
+ if (data.toUpperCase().startsWith(SCOREMATRIX))
+ {
+ /*
+ * Parse name from ScoreMatrix <name>
+ */
+ if (name != null)
+ {
+ System.err
+ .println("Warning: 'ScoreMatrix' repeated in file at line "
+ + lineNo);
+ }
+ StringTokenizer nameLine = new StringTokenizer(data, DELIMITERS);
+ if (nameLine.countTokens() != 2)
+ {
+ err = "Format error: expected 'ScoreMatrix <name>', found '"
+ + data + "' at line " + lineNo;
+ throw new FileFormatException(err);
+ }
+ nameLine.nextToken();
+ name = nameLine.nextToken();
+ continue;
+ }
+ else if (name == null)
+ {
+ err = "Format error: 'ScoreMatrix <name>' should be the first non-comment line";
+ throw new FileFormatException(err);
+ }
+
+ /*
+ * next line after ScoreMatrix should be the alphabet of scored symbols
+ */
+ if (alphabet == null)
+ {
+ alphabet = data;
+ size = alphabet.length();
+ scores = new float[size][];
+ continue;
+ }
+
+ /*
+ * too much information
+ */
+ if (row >= size)
+ {
+ err = "Unexpected extra input line in score model file: '" + data
+ + "'";
+ throw new FileFormatException(err);
+ }
+
+ /*
+ * subsequent lines should be the symbol scores
+ * optionally with the symbol as the first column for readability
+ */
+ StringTokenizer scoreLine = new StringTokenizer(data, DELIMITERS);
+ if (scoreLine.countTokens() == size + 1)
+ {
+ /*
+ * check 'guide' symbol is the row'th letter of the alphabet
+ */
+ String symbol = scoreLine.nextToken();
+ if (symbol.length() > 1 || symbol.charAt(0) != alphabet.charAt(row))
+ {
+ err = String
+ .format("Error parsing score matrix at line %d, expected '%s' but found '%s'",
+ lineNo, alphabet.charAt(row), symbol);
+ throw new FileFormatException(err);
+ }
+ }
+ if (scoreLine.countTokens() != size)
+ {
+ err = String.format("Expected %d scores at line %d but found %d",
+ size, lineNo, scoreLine.countTokens());
+ throw new FileFormatException(err);
+ }
+ scores[row] = new float[size];
+ int col = 0;
+ String value = null;
+ while (scoreLine.hasMoreTokens())
+ {
+ try
+ {
+ value = scoreLine.nextToken();
+ scores[row][col] = Float.valueOf(value);
+ col++;
+ } catch (NumberFormatException e)
+ {
+ err = String.format(
+ "Invalid score value '%s' at line %d column %d", value,
+ lineNo, col);
+ throw new FileFormatException(err);
+ }
+ }
+ row++;
+ }
+
+ /*
+ * out of data - check we found enough
+ */
+ if (row < size)
+ {
+ err = String
+ .format("Expected %d rows of score data in score matrix but only found %d",
+ size, row);
+ throw new FileFormatException(err);
+ }
+
+ /*
+ * If we get here, then name, alphabet and scores have been parsed successfully
+ */
+ sm = new ScoreMatrix(name, alphabet.toCharArray(), scores);
+ matrixName = name;
+
+ return sm;
+ }
+
+ public String getMatrixName()
+ {
+ return matrixName;
+ }
+}
package jalview.analysis.scoremodels;
import static org.testng.Assert.assertEquals;
-import static org.testng.Assert.assertFalse;
-import static org.testng.Assert.assertNotNull;
-import static org.testng.Assert.assertNull;
-import static org.testng.Assert.assertTrue;
-
-import java.io.ByteArrayInputStream;
import org.testng.annotations.Test;
}
}
}
-
- /**
- * Test a successful parse of a (small) score matrix file
- */
- @Test(groups = "Functional")
- public void testParse()
- {
- /*
- * some messy but valid input data, with comma, space
- * or tab (or combinations) as score value delimiters
- * this example includes 'guide' symbols on score rows
- */
- String data = "ScoreMatrix MyTest\n" + "ATU tx-\n"
- + "A,1.1,1.2,1.3,1.4, 1.5, 1.6, 1.7\n"
- + "T,2.1 2.2 2.3 2.4 2.5 2.6 2.7\n"
- + "U\t3.1\t3.2\t3.3\t3.4\t3.5\t3.6\t3.7\n"
- + " 4.1 ,4.2,\t,4.3 ,\t4.4\t, \4.5,4.6 4.7\n"
- + "t, 5.1,5.3,5.3,5.4,5.5, 5.6, 5.7\n"
- + "x\t6.1, 6.2 6.3 6.4 6.5 6.6 6.7\n"
- + "-, \t7.1\t7.2 7.3, 7.4, 7.5\t,7.6,7.7\n";
- ScoreMatrix sm = ScoreMatrix.parse(new ByteArrayInputStream(data
- .getBytes()));
- assertNotNull(sm);
- assertEquals(sm.getName(), "MyTest");
- assertTrue(sm.isDNA());
- assertFalse(sm.isProtein());
- assertEquals(sm.getPairwiseScore('A', 'A'), 1.1f);
- assertEquals(sm.getPairwiseScore('A', 'T'), 1.2f);
- assertEquals(sm.getPairwiseScore('a', 'T'), 1.2f); // A/a equivalent
- assertEquals(sm.getPairwiseScore('A', 't'), 1.5f); // T/t not equivalent
- assertEquals(sm.getPairwiseScore('a', 't'), 1.5f);
- assertEquals(sm.getPairwiseScore('T', ' '), 2.4f);
- assertEquals(sm.getPairwiseScore('U', 'x'), 3.6f);
- assertEquals(sm.getPairwiseScore('u', 'x'), 3.6f);
- assertEquals(sm.getPairwiseScore('U', 'X'), 0f); // X (upper) unmapped
- assertEquals(sm.getPairwiseScore('A', '.'), 0f); // . unmapped
- assertEquals(sm.getPairwiseScore('-', '-'), 7.7f);
- assertEquals(sm.getPairwiseScore('A', (char) 128), 0f); // out of range
-
- /*
- * without guide symbols on score rows
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n3 4\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNotNull(sm);
- assertEquals(sm.getPairwiseScore('X', 'X'), 1f);
- assertEquals(sm.getPairwiseScore('X', 'y'), 2f);
- assertEquals(sm.getPairwiseScore('y', 'x'), 3f);
- assertEquals(sm.getPairwiseScore('y', 'Y'), 4f);
- assertEquals(sm.getPairwiseScore('D', 'R'), 0f);
- }
-
- @Test(groups = "Functional")
- public void testParse_invalidInput()
- {
- /*
- * valid first
- */
- String data = "ScoreMatrix MyTest\nXY\n1 2\n3 4\n";
- ScoreMatrix sm = ScoreMatrix.parse(new ByteArrayInputStream(data
- .getBytes()));
- assertNotNull(sm);
-
- /*
- * Name missing
- */
- data = "ScoreMatrix\nXY\n1 2\n3 4\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * ScoreMatrix header missing
- */
- data = "XY\n1 2\n3 4\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Not enough rows
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Not enough columns
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n3\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Too many columns
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n3 4 5\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Too many rows
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n3 4\n6 7";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * unsupported delimiter |
- */
- data = "ScoreMatrix MyTest\nXY\n1|2\n3|4\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Bad float value
- */
- data = "ScoreMatrix MyTest\nXY\n1 2\n3 four\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
-
- /*
- * Bad guide character on scores row
- */
- data = "ScoreMatrix MyTest\nXY\nX 1 2\ny 3 4\n";
- sm = ScoreMatrix.parse(new ByteArrayInputStream(data.getBytes()));
- assertNull(sm);
- }
}
{
"examples/testdata/cullpdb_pc25_res3.0_R0.3_d150729_chains9361.fasta.15316",
FileFormat.Fasta },
-
+ { "resources/scoreModel/pam250.scm", FileFormat.ScoreMatrix }
// { "examples/testdata/test.amsa", "AMSA" },
// { "examples/test.jnet", "JnetFile" },
};
--- /dev/null
+package jalview.io;
+
+import static org.testng.Assert.assertEquals;
+import static org.testng.Assert.assertFalse;
+import static org.testng.Assert.assertNotNull;
+import static org.testng.Assert.assertTrue;
+import static org.testng.Assert.fail;
+
+import jalview.analysis.scoremodels.ScoreMatrix;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+
+import org.testng.annotations.Test;
+
+public class ScoreMatrixFileTest
+{
+
+ /**
+ * Test a successful parse of a (small) score matrix file
+ *
+ * @throws IOException
+ * @throws MalformedURLException
+ */
+ @Test(groups = "Functional")
+ public void testParse() throws MalformedURLException, IOException
+ {
+ /*
+ * some messy but valid input data, with comma, space
+ * or tab (or combinations) as score value delimiters
+ * this example includes 'guide' symbols on score rows
+ */
+ String data = "ScoreMatrix MyTest\n" + "ATU tx-\n"
+ + "A,1.1,1.2,1.3,1.4, 1.5, 1.6, 1.7\n"
+ + "T,2.1 2.2 2.3 2.4 2.5 2.6 2.7\n"
+ + "U\t3.1\t3.2\t3.3\t3.4\t3.5\t3.6\t3.7\n"
+ + " 4.1 ,4.2,\t,4.3 ,\t4.4\t, \4.5,4.6 4.7\n"
+ + "t, 5.1,5.3,5.3,5.4,5.5, 5.6, 5.7\n"
+ + "x\t6.1, 6.2 6.3 6.4 6.5 6.6 6.7\n"
+ + "-, \t7.1\t7.2 7.3, 7.4, 7.5\t,7.6,7.7\n";
+ FileParse fp = new FileParse(data, DataSourceType.PASTE);
+ ScoreMatrixFile parser = new ScoreMatrixFile(fp);
+ ScoreMatrix sm = parser.parseMatrix();
+
+ assertNotNull(sm);
+ assertEquals(sm.getName(), "MyTest");
+ assertTrue(sm.isDNA());
+ assertFalse(sm.isProtein());
+ assertEquals(sm.getPairwiseScore('A', 'A'), 1.1f);
+ assertEquals(sm.getPairwiseScore('A', 'T'), 1.2f);
+ assertEquals(sm.getPairwiseScore('a', 'T'), 1.2f); // A/a equivalent
+ assertEquals(sm.getPairwiseScore('A', 't'), 1.5f); // T/t not equivalent
+ assertEquals(sm.getPairwiseScore('a', 't'), 1.5f);
+ assertEquals(sm.getPairwiseScore('T', ' '), 2.4f);
+ assertEquals(sm.getPairwiseScore('U', 'x'), 3.6f);
+ assertEquals(sm.getPairwiseScore('u', 'x'), 3.6f);
+ assertEquals(sm.getPairwiseScore('U', 'X'), 0f); // X (upper) unmapped
+ assertEquals(sm.getPairwiseScore('A', '.'), 0f); // . unmapped
+ assertEquals(sm.getPairwiseScore('-', '-'), 7.7f);
+ assertEquals(sm.getPairwiseScore('A', (char) 128), 0f); // out of range
+
+ /*
+ * without guide symbols on score rows
+ */
+ data = "ScoreMatrix MyTest\nXY\n1 2\n3 4\n";
+ fp = new FileParse(data, DataSourceType.PASTE);
+ parser = new ScoreMatrixFile(fp);
+ sm = parser.parseMatrix();
+ assertNotNull(sm);
+ assertEquals(sm.getPairwiseScore('X', 'X'), 1f);
+ assertEquals(sm.getPairwiseScore('X', 'y'), 2f);
+ assertEquals(sm.getPairwiseScore('y', 'x'), 3f);
+ assertEquals(sm.getPairwiseScore('y', 'Y'), 4f);
+ assertEquals(sm.getPairwiseScore('D', 'R'), 0f);
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_headerMissing()
+ {
+ String data;
+
+ data = "XY\n1 2\n3 4\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Format error: 'ScoreMatrix <name>' should be the first non-comment line");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_notEnoughRows()
+ {
+ String data = "ScoreMatrix MyTest\nXY\n1 2\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Expected 2 rows of score data in score matrix but only found 1");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_notEnoughColumns()
+ {
+ String data = "ScoreMatrix MyTest\nXY\n1 2\n3\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Expected 2 scores at line 4 but found 1");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_tooManyColumns()
+ {
+ /*
+ * with two too many columns:
+ */
+ String data = "ScoreMatrix MyTest\nXY\n1 2\n3 4 5 6\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Expected 2 scores at line 4 but found 4");
+ }
+
+ /*
+ * with guide character and one too many columns:
+ */
+ data = "ScoreMatrix MyTest\nXY\nX 1 2\nY 3 4 5\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Expected 2 scores at line 4 but found 4");
+ }
+
+ /*
+ * with no guide character and one too many columns:
+ * parser guesses the first column is the guide character
+ */
+ data = "ScoreMatrix MyTest\nXY\n1 2\n3 4 5\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Error parsing score matrix at line 4, expected 'Y' but found '3'");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_tooManyRows()
+ {
+ String data = "ScoreMatrix MyTest\nXY\n1 2\n3 4\n6 7";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Unexpected extra input line in score model file: '6 7'");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_badDelimiter()
+ {
+ String data = "ScoreMatrix MyTest\nXY\n1|2\n3|4\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Expected 2 scores at line 3 but found 1");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_badFloat()
+ {
+ String data = "ScoreMatrix MyTest\nXY\n1 2\n3 four\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Invalid score value 'four' at line 4 column 1");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_badGuideCharacter()
+ {
+ String data = "ScoreMatrix MyTest\nXY\nX 1 2\ny 3 4\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(e.getMessage(),
+ "Error parsing score matrix at line 4, expected 'Y' but found 'y'");
+ }
+ }
+
+ @Test(groups = "Functional")
+ public void testParse_nameMissing()
+ {
+ /*
+ * Name missing
+ */
+ String data = "ScoreMatrix\nXY\n1 2\n3 4\n";
+ try
+ {
+ new ScoreMatrixFile(new FileParse(data, DataSourceType.PASTE))
+ .parseMatrix();
+ fail("expected exception");
+ } catch (IOException e)
+ {
+ assertEquals(
+ e.getMessage(),
+ "Format error: expected 'ScoreMatrix <name>', found 'ScoreMatrix' at line 1");
+ }
+ }
+}
git://source.jalview.org / jalview.git / commitdiff