X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FStringUtils.java;h=3c5ba92f097af2a2fa4b4e8836a8ae2528d632b5;hb=5cb4c1540eaca054c26ff42a8319f0dbffb1f8e6;hp=b5ab40df65c9c121000b017044ee344eb3e84b0d;hpb=37de9310bec3501cbc6381e0c3dcb282fcaad812;p=jalview.git

diff --git a/src/jalview/util/StringUtils.java b/src/jalview/util/StringUtils.java
index b5ab40d..3c5ba92 100644
--- a/src/jalview/util/StringUtils.java
+++ b/src/jalview/util/StringUtils.java
@@ -107,29 +107,6 @@ public class StringUtils
   }
 
   /**
-   * Returns the last part of 'input' after the last occurrence of 'token'. For
-   * example to extract only the filename from a full path or URL.
-   * 
-   * @param input
-   * @param token
-   *          a delimiter which must be in regular expression format
-   * @return
-   */
-  public static String getLastToken(String input, String token)
-  {
-    if (input == null)
-    {
-      return null;
-    }
-    if (token == null)
-    {
-      return input;
-    }
-    String[] st = input.split(token);
-    return st[st.length - 1];
-  }
-
-  /**
    * Parses the input string into components separated by the delimiter. Unlike
    * String.split(), this method will ignore occurrences of the delimiter which
    * are nested within single quotes in name-value pair values, e.g. a='b,c'.
@@ -138,14 +115,15 @@ public class StringUtils
    * @param delimiter
    * @return elements separated by separator
    */
-  public static String[] separatorListToArray(String input, String delimiter)
+  public static String[] separatorListToArray(String input,
+          String delimiter)
   {
     int seplen = delimiter.length();
     if (input == null || input.equals("") || input.equals(delimiter))
     {
       return null;
     }
-    List<String> jv = new ArrayList<String>();
+    List<String> jv = new ArrayList<>();
     int cp = 0, pos, escape;
     boolean wasescaped = false, wasquoted = false;
     String lstitem = null;
@@ -155,9 +133,8 @@ public class StringUtils
       if (wasescaped || wasquoted)
       {
         // append to previous pos
-        jv.set(jv.size() - 1,
-                lstitem = lstitem + delimiter
-                        + input.substring(cp, pos + escape));
+        jv.set(jv.size() - 1, lstitem = lstitem + delimiter
+                + input.substring(cp, pos + escape));
       }
       else
       {
@@ -201,8 +178,8 @@ public class StringUtils
     }
     if (DEBUG)
     {
-      System.err.println("Empty Array from '" + delimiter
-              + "' separated List");
+      System.err.println(
+              "Empty Array from '" + delimiter + "' separated List");
     }
     return null;
   }
@@ -235,16 +212,16 @@ public class StringUtils
       }
       if (DEBUG)
       {
-        System.err.println("Returning '" + separator
-                + "' separated List:\n");
+        System.err
+                .println("Returning '" + separator + "' separated List:\n");
         System.err.println(v);
       }
       return v.toString();
     }
     if (DEBUG)
     {
-      System.err.println("Returning empty '" + separator
-              + "' separated List\n");
+      System.err.println(
+              "Returning empty '" + separator + "' separated List\n");
     }
     return "" + separator;
   }
@@ -364,8 +341,8 @@ public class StringUtils
         }
       } catch (NumberFormatException e)
       {
-        System.err.println("Invalid version format found: "
-                + e.getMessage());
+        System.err
+                .println("Invalid version format found: " + e.getMessage());
         return 0;
       }
     }
@@ -403,4 +380,45 @@ public class StringUtils
     }
     return s.substring(0, 1).toUpperCase() + s.substring(1).toLowerCase();
   }
+
+  /**
+   * A helper method that strips off any leading or trailing html and body tags.
+   * If no html tag is found, then also html-encodes angle bracket characters.
+   * 
+   * @param text
+   * @return
+   */
+  public static String stripHtmlTags(String text)
+  {
+    if (text == null)
+    {
+      return null;
+    }
+    String tmp2up = text.toUpperCase();
+    int startTag = tmp2up.indexOf("<HTML>");
+    if (startTag > -1)
+    {
+      text = text.substring(startTag + 6);
+      tmp2up = tmp2up.substring(startTag + 6);
+    }
+    // is omission of "<BODY>" intentional here??
+    int endTag = tmp2up.indexOf("</BODY>");
+    if (endTag > -1)
+    {
+      text = text.substring(0, endTag);
+      tmp2up = tmp2up.substring(0, endTag);
+    }
+    endTag = tmp2up.indexOf("</HTML>");
+    if (endTag > -1)
+    {
+      text = text.substring(0, endTag);
+    }
+  
+    if (startTag == -1 && (text.contains("<") || text.contains(">")))
+    {
+      text = text.replaceAll("<", "&lt;");
+      text = text.replaceAll(">", "&gt;");
+    }
+    return text;
+  }
 }