import jalview.util.Comparison;
import jalview.util.Format;
import jalview.util.MessageManager;
-import jalview.util.Platform;
import java.io.BufferedReader;
import java.io.FileReader;
{
private static final String ANNOTATION = "annotation";
- // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using
- // NOT_RNASS first.
+// private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "(");
+//
+// private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")");
- public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz";
-
- public static final int REGEX_STOCKHOLM = 0;
+ public static final Regex DETECT_BRACKETS = new Regex(
+ "(<|>|\\[|\\]|\\(|\\)|\\{|\\})");
- public static final int REGEX_BRACKETS = 1;
+ // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using NOT_RNASS first.
+ public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz";
// use the following regex to decide an annotations (whole) line is NOT an RNA
// SS (it contains only E,H,e,h and other non-brace/non-alpha chars)
- public static final int REGEX_NOT_RNASS = 2;
-
- private static final int REGEX_ANNOTATION = 3;
-
- private static final int REGEX_PFAM = 4;
-
- private static final int REGEX_RFAM = 5;
-
- private static final int REGEX_ALIGN_END = 6;
-
- private static final int REGEX_SPLIT_ID = 7;
-
- private static final int REGEX_SUBTYPE = 8;
-
- private static final int REGEX_ANNOTATION_LINE = 9;
-
- private static final int REGEX_REMOVE_ID = 10;
-
- private static final int REGEX_OPEN_PAREN = 11;
-
- private static final int REGEX_CLOSE_PAREN = 12;
-
- public static final int REGEX_MAX = 13;
-
- private static Regex REGEX[] = new Regex[REGEX_MAX];
-
- /**
- * Centralize all actual Regex instantialization in Platform.
- *
- * @param id
- * @return
- */
- private static Regex getRegex(int id)
- {
- if (REGEX[id] == null)
- {
- String pat = null, pat2 = null;
- switch (id)
- {
- case REGEX_STOCKHOLM:
- pat = "# STOCKHOLM ([\\d\\.]+)";
- break;
- case REGEX_BRACKETS:
- // for reference; not used
- pat = "(<|>|\\[|\\]|\\(|\\)|\\{|\\})";
- break;
- case REGEX_NOT_RNASS:
- pat = "^[^<>[\\](){}A-DF-Za-df-z]*$";
- break;
- case REGEX_ANNOTATION:
- pat = "(\\w+)\\s*(.*)";
- break;
- case REGEX_PFAM:
- pat = "PF[0-9]{5}(.*)";
- break;
- case REGEX_RFAM:
- pat = "RF[0-9]{5}(.*)";
- break;
- case REGEX_ALIGN_END:
- pat = "^\\s*\\/\\/";
- break;
- case REGEX_SPLIT_ID:
- pat = "(\\S+)\\/(\\d+)\\-(\\d+)";
- break;
- case REGEX_SUBTYPE:
- pat = "(\\S+)\\s+(\\S*)\\s+(.*)";
- break;
- case REGEX_ANNOTATION_LINE:
- pat = "#=(G[FSRC]?)\\s+(.*)";
- break;
- case REGEX_REMOVE_ID:
- pat = "(\\S+)\\s+(\\S+)";
- break;
- case REGEX_OPEN_PAREN:
- pat = "(<|\\[)";
- pat2 = "(";
- break;
- case REGEX_CLOSE_PAREN:
- pat = "(>|\\])";
- pat2 = ")";
- break;
- default:
- return null;
- }
- REGEX[id] = Platform.newRegex(pat, pat2);
- }
- return REGEX[id];
- }
+ private static final Regex NOT_RNASS = new Regex(
+ "^[^<>[\\](){}A-DF-Za-df-z]*$");
StringBuffer out; // output buffer
// First, we have to check that this file has STOCKHOLM format, i.e. the
// first line must match
- r = getRegex(REGEX_STOCKHOLM);
+ r = new Regex("# STOCKHOLM ([\\d\\.]+)");
if (!r.search(nextLine()))
{
throw new IOException(MessageManager
}
// We define some Regexes here that will be used regularily later
- rend = getRegex(REGEX_ALIGN_END);//"^\\s*\\/\\/"); // Find the end of an alignment
- p = getRegex(REGEX_SPLIT_ID);//"(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
+ rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
+ p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
// id/from/to
- s = getRegex(REGEX_SUBTYPE);// "(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses
- // annotation subtype
- r = getRegex(REGEX_ANNOTATION_LINE);// "#=(G[FSRC]?)\\s+(.*)"); // Finds any
- // annotation line
- x = getRegex(REGEX_REMOVE_ID);// "(\\S+)\\s+(\\S+)"); // split id from
- // sequence
+ s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
+ r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
+ x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
// Convert all bracket types to parentheses (necessary for passing to VARNA)
- Regex openparen = getRegex(REGEX_OPEN_PAREN);//"(<|\\[)", "(");
- Regex closeparen = getRegex(REGEX_CLOSE_PAREN);//"(>|\\])", ")");
+ Regex openparen = new Regex("(<|\\[)", "(");
+ Regex closeparen = new Regex("(>|\\])", ")");
// // Detect if file is RNA by looking for bracket types
- // Regex detectbrackets = getRegex("(<|>|\\[|\\]|\\(|\\))");
+// Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
rend.optimize();
p.optimize();
this.noSeqs = seqs.size();
String dbsource = null;
- Regex pf = getRegex(REGEX_PFAM); // Finds AC for Pfam
- Regex rf = getRegex(REGEX_RFAM); // Finds AC for Rfam
+ Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
+ Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
if (getAlignmentProperty("AC") != null)
{
String dbType = getAlignmentProperty("AC").toString();
*/
// Let's save the annotations, maybe we'll be able to do something
// with them later...
- Regex an = getRegex(REGEX_ANNOTATION);
+ Regex an = new Regex("(\\w+)\\s*(.*)");
if (an.search(annContent))
{
if (an.stringMatched(1).equals("NH"))
if (type.equalsIgnoreCase("secondary structure"))
{
ss = true;
- isrnass = !getRegex(REGEX_NOT_RNASS).search(annots); // sorry about the double
- // negative
+ isrnass = !NOT_RNASS.search(annots); // sorry about the double negative
// here (it's easier for dealing with
// other non-alpha-non-brace chars)
}
while (en.hasMoreElements())
{
Object idd = en.nextElement();
- String type = dataRef.remove(idd);
+ String type = (String) dataRef.remove(idd);
out.append(new Format("%-" + (maxid - 2) + "s")
.form("#=GS " + idd.toString() + " "));
if (type.contains("PFAM") || type.contains("RFAM"))