/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
* Jalview is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
*
* Jalview is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
* PURPOSE. See the GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
* The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.util;
+import static jalview.util.UrlConstants.SEQUENCE_ID;
+import static jalview.util.UrlConstants.SEQUENCE_NAME;
+
import java.util.Vector;
public class UrlLink
private boolean dynamic = false;
+ private boolean uses_seq_id = false;
+
private String invalidMessage = null;
/**
*/
public UrlLink(String link)
{
- int sep = link.indexOf("|"), psqid = link.indexOf("$SEQUENCE_ID");
+ int sep = link.indexOf("|");
+ int psqid = link.indexOf("$" + SEQUENCE_ID);
+ int nsqid = link.indexOf("$" + SEQUENCE_NAME);
if (psqid > -1)
{
dynamic = true;
- int p = sep;
- do
- {
- sep = p;
- p = link.indexOf("|", sep + 1);
- } while (p > sep && p < psqid);
- // Assuming that the URL itself does not contain any '|' symbols
- // sep now contains last pipe symbol position prior to any regex symbols
- label = link.substring(0, sep);
- if (label.indexOf("|") > -1)
- {
- // | terminated database name / www target at start of Label
- target = label.substring(0, label.indexOf("|"));
- }
- else if (label.indexOf(" ") > 2)
- {
- // space separated Label - matches database name
- target = label.substring(0, label.indexOf(" "));
- }
- else
- {
- target = label;
- }
- // Parse URL : Whole URL string first
- url_prefix = link.substring(sep + 1, psqid);
- if (link.indexOf("$SEQUENCE_ID=/") == psqid
- && (p = link.indexOf("/=$", psqid + 14)) > psqid + 14)
- {
- // Extract Regex and suffix
- url_suffix = link.substring(p + 3);
- regexReplace = link.substring(psqid + 14, p);
- try
- {
- com.stevesoft.pat.Regex rg = com.stevesoft.pat.Regex.perlCode("/"
- + regexReplace + "/");
- if (rg == null)
- {
- invalidMessage = "Invalid Regular Expression : '"
- + regexReplace + "'\n";
- }
- } catch (Exception e)
- {
- invalidMessage = "Invalid Regular Expression : '" + regexReplace
- + "'\n";
- }
- }
- else
- {
- regexReplace = null;
- // verify format is really correct.
- if (link.indexOf("$SEQUENCE_ID$") == psqid)
- {
- url_suffix = link.substring(psqid + 13);
- regexReplace = null;
- }
- else
- {
- invalidMessage = "Warning: invalid regex structure for URL link : "
- + link;
- }
- }
+ uses_seq_id = true;
+
+ sep = parseTargetAndLabel(sep, psqid, link);
+
+ parseUrl(link, SEQUENCE_ID, psqid, sep);
+ }
+ else if (nsqid > -1)
+ {
+ dynamic = true;
+ sep = parseTargetAndLabel(sep, nsqid, link);
+
+ parseUrl(link, SEQUENCE_NAME, nsqid, sep);
}
else
{
target = link.substring(0, sep);
- label = link.substring(0, sep = link.lastIndexOf("|"));
+ sep = link.lastIndexOf("|");
+ label = link.substring(0, sep);
url_prefix = link.substring(sep + 1);
regexReplace = null; // implies we trim any prefix if necessary //
// regexReplace=".*\\|?(.*)";
url_suffix = null;
}
+
+ label = label.trim();
+ target = target.trim();
+ target = target.toUpperCase(); // DBRefEntry uppercases DB names
+ // NB getCanonicalName might be better but does not currently change case
}
/**
if (ns == 0)
{
// take whole regex
- return new String[]
- { rg.stringMatched(),
+ return new String[] { rg.stringMatched(),
url_prefix + rg.stringMatched() + url_suffix };
} /*
* else if (ns==1) { // take only subgroup match return new String[]
}
// just return simple url substitution.
- return new String[]
- { idstring, url_prefix + idstring + url_suffix };
+ return new String[] { idstring, url_prefix + idstring + url_suffix };
}
else
{
- return new String[]
- { "", url_prefix };
+ return new String[] { "", url_prefix };
}
}
+ @Override
public String toString()
{
+ String var = (uses_seq_id ? SEQUENCE_ID : SEQUENCE_NAME);
+
return label
+ "|"
+ url_prefix
- + (dynamic ? ("$SEQUENCE_ID" + ((regexReplace != null) ? "="
+ + (dynamic ? ("$" + var + ((regexReplace != null) ? "="
+ regexReplace + "=$" : "$")) : "")
+ ((url_suffix == null) ? "" : url_suffix);
+ }
+
+ /**
+ *
+ * @param firstSep
+ * Location of first occurrence of separator in link string
+ * @param psqid
+ * Position of sequence id or name in link string
+ * @param link
+ * Link string containing database name and url
+ * @return Position of last separator symbol prior to any regex symbols
+ */
+ protected int parseTargetAndLabel(int firstSep, int psqid, String link)
+ {
+ int p = firstSep;
+ int sep = firstSep;
+ do
+ {
+ sep = p;
+ p = link.indexOf("|", sep + 1);
+ } while (p > sep && p < psqid);
+ // Assuming that the URL itself does not contain any '|' symbols
+ // sep now contains last pipe symbol position prior to any regex symbols
+ label = link.substring(0, sep);
+ if (label.indexOf("|") > -1)
+ {
+ // | terminated database name / www target at start of Label
+ target = label.substring(0, label.indexOf("|"));
+ }
+ else if (label.indexOf(" ") > 2)
+ {
+ // space separated Label - matches database name
+ target = label.substring(0, label.indexOf(" "));
+ }
+ else
+ {
+ target = label;
+ }
+ return sep;
+ }
+
+ /**
+ * Parse the URL part of the link string
+ *
+ * @param link
+ * Link string containing database name and url
+ * @param varName
+ * Name of variable in url string (e.g. SEQUENCE_ID, SEQUENCE_NAME)
+ * @param sqidPos
+ * Position of id or name in link string
+ * @param sep
+ * Position of separator in link string
+ */
+ protected void parseUrl(String link, String varName, int sqidPos, int sep)
+ {
+ url_prefix = link.substring(sep + 1, sqidPos);
+
+ // delimiter at start of regex: e.g. $SEQUENCE_ID=/
+ String startDelimiter = "$" + varName + "=/";
+
+ // delimiter at end of regex: /=$
+ String endDelimiter = "/=$";
+ int startLength = startDelimiter.length();
+
+ // Parse URL : Whole URL string first
+ int p = link.indexOf(endDelimiter, sqidPos + startLength);
+
+ if (link.indexOf(startDelimiter) == sqidPos
+ && (p > sqidPos + startLength))
+ {
+ // Extract Regex and suffix
+ url_suffix = link.substring(p + endDelimiter.length());
+ regexReplace = link.substring(sqidPos + startLength, p);
+ try
+ {
+ com.stevesoft.pat.Regex rg = com.stevesoft.pat.Regex.perlCode("/"
+ + regexReplace + "/");
+ if (rg == null)
+ {
+ invalidMessage = "Invalid Regular Expression : '" + regexReplace
+ + "'\n";
+ }
+ } catch (Exception e)
+ {
+ invalidMessage = "Invalid Regular Expression : '" + regexReplace
+ + "'\n";
+ }
+ }
+ else
+ {
+ // no regex
+ regexReplace = null;
+ // verify format is really correct.
+ if (link.indexOf("$" + varName + "$") == sqidPos)
+ {
+ url_suffix = link.substring(sqidPos + startLength - 1);
+ regexReplace = null;
+ }
+ else
+ {
+ invalidMessage = "Warning: invalid regex structure for URL link : "
+ + link;
+ }
+ }
}
private static void testUrls(UrlLink ul, String idstring, String[] urls)
public static void main(String argv[])
{
- String[] links = new String[]
- {
+ String[] links = new String[] {
/*
* "AlinkT|Target|http://foo.foo.soo/",
* "myUrl1|http://$SEQUENCE_ID=/[0-9]+/=$.someserver.org/foo",
* "PF3|http://us.expasy.org/cgi-bin/niceprot.pl?$SEQUENCE_ID=/PFAM:(.+)/=$"
* , "NOTFER|http://notfer.org/$SEQUENCE_ID=/(?<!\\s)(.+)/=$",
*/
- "NESTED|http://nested/$SEQUENCE_ID=/^(?:Label:)?(?:(?:gi\\|(\\d+))|([^:]+))/=$/nested" };
- String[] idstrings = new String[]
- {
+ "NESTED|http://nested/$" + SEQUENCE_ID
+ + "=/^(?:Label:)?(?:(?:gi\\|(\\d+))|([^:]+))/=$/nested" };
+ String[] idstrings = new String[] {
/*
* //"LGUL_human", //"QWIQW_123123", "uniprot|why_do+_12313_foo",
* //"123123312", "123123 ABCDE foo", "PFAM:PF23943",
return dynamic;
}
+ public boolean usesSeqId()
+ {
+ return uses_seq_id;
+ }
+
public void setLabel(String newlabel)
{
this.label = newlabel;