X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FStringUtils.java;h=89bc36d65d72904132bc833a3b62c83130a5e5a9;hb=HEAD;hp=b5ab40df65c9c121000b017044ee344eb3e84b0d;hpb=37de9310bec3501cbc6381e0c3dcb282fcaad812;p=jalview.git

diff --git a/src/jalview/util/StringUtils.java b/src/jalview/util/StringUtils.java
index b5ab40d..89bc36d 100644
--- a/src/jalview/util/StringUtils.java
+++ b/src/jalview/util/StringUtils.java
@@ -20,8 +20,12 @@
  */
 package jalview.util;
 
+import java.io.UnsupportedEncodingException;
+import java.net.URLEncoder;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Locale;
+import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
 public class StringUtils
@@ -29,8 +33,16 @@ public class StringUtils
   private static final Pattern DELIMITERS_PATTERN = Pattern
           .compile(".*='[^']*(?!')");
 
+  private static final char PERCENT = '%';
+
   private static final boolean DEBUG = false;
 
+  /*
+   * URL encoded characters, indexed by char value
+   * e.g. urlEncodings['='] = urlEncodings[61] = "%3D"
+   */
+  private static String[] urlEncodings = new String[255];
+
   /**
    * Returns a new character array, after inserting characters into the given
    * character array.
@@ -138,14 +150,15 @@ 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 +168,8 @@ 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
       {
@@ -190,19 +202,19 @@ public class StringUtils
       jv.clear();
       if (DEBUG)
       {
-        System.err.println("Array from '" + delimiter
+        jalview.bin.Console.errPrintln("Array from '" + delimiter
                 + "' separated List:\n" + v.length);
         for (int i = 0; i < v.length; i++)
         {
-          System.err.println("item " + i + " '" + v[i] + "'");
+          jalview.bin.Console.errPrintln("item " + i + " '" + v[i] + "'");
         }
       }
       return v;
     }
     if (DEBUG)
     {
-      System.err.println("Empty Array from '" + delimiter
-              + "' separated List");
+      jalview.bin.Console.errPrintln(
+              "Empty Array from '" + delimiter + "' separated List");
     }
     return null;
   }
@@ -235,16 +247,16 @@ public class StringUtils
       }
       if (DEBUG)
       {
-        System.err.println("Returning '" + separator
-                + "' separated List:\n");
-        System.err.println(v);
+        System.err
+                .println("Returning '" + separator + "' separated List:\n");
+        jalview.bin.Console.errPrintln(v);
       }
       return v.toString();
     }
     if (DEBUG)
     {
-      System.err.println("Returning empty '" + separator
-              + "' separated List\n");
+      jalview.bin.Console.errPrintln(
+              "Returning empty '" + separator + "' separated List\n");
     }
     return "" + separator;
   }
@@ -364,8 +376,8 @@ 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;
       }
     }
@@ -399,8 +411,237 @@ public class StringUtils
     }
     if (s.length() <= 1)
     {
-      return s.toUpperCase();
+      return s.toUpperCase(Locale.ROOT);
+    }
+    return s.substring(0, 1).toUpperCase(Locale.ROOT)
+            + s.substring(1).toLowerCase(Locale.ROOT);
+  }
+
+  /**
+   * 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(Locale.ROOT);
+    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;
+  }
+
+  /**
+   * Answers the input string with any occurrences of the 'encodeable'
+   * characters replaced by their URL encoding
+   * 
+   * @param s
+   * @param encodable
+   * @return
+   */
+  public static String urlEncode(String s, String encodable)
+  {
+    if (s == null || s.isEmpty())
+    {
+      return s;
+    }
+
+    /*
+     * do % encoding first, as otherwise it may double-encode!
+     */
+    if (encodable.indexOf(PERCENT) != -1)
+    {
+      s = urlEncode(s, PERCENT);
+    }
+
+    for (char c : encodable.toCharArray())
+    {
+      if (c != PERCENT)
+      {
+        s = urlEncode(s, c);
+      }
+    }
+    return s;
+  }
+
+  /**
+   * Answers the input string with any occurrences of {@code c} replaced with
+   * their url encoding. Answers the input string if it is unchanged.
+   * 
+   * @param s
+   * @param c
+   * @return
+   */
+  static String urlEncode(String s, char c)
+  {
+    String decoded = String.valueOf(c);
+    if (s.indexOf(decoded) != -1)
+    {
+      String encoded = getUrlEncoding(c);
+      if (!encoded.equals(decoded))
+      {
+        s = s.replace(decoded, encoded);
+      }
+    }
+    return s;
+  }
+
+  /**
+   * Answers the input string with any occurrences of the specified (unencoded)
+   * characters replaced by their URL decoding.
+   * <p>
+   * Example: {@code urlDecode("a%3Db%3Bc", "-;=,")} should answer
+   * {@code "a=b;c"}.
+   * 
+   * @param s
+   * @param encodable
+   * @return
+   */
+  public static String urlDecode(String s, String encodable)
+  {
+    if (s == null || s.isEmpty())
+    {
+      return s;
+    }
+
+    for (char c : encodable.toCharArray())
+    {
+      String encoded = getUrlEncoding(c);
+      if (s.indexOf(encoded) != -1)
+      {
+        String decoded = String.valueOf(c);
+        s = s.replace(encoded, decoded);
+      }
+    }
+    return s;
+  }
+
+  /**
+   * Does a lazy lookup of the url encoding of the given character, saving the
+   * value for repeat lookups
+   * 
+   * @param c
+   * @return
+   */
+  private static String getUrlEncoding(char c)
+  {
+    if (c < 0 || c >= urlEncodings.length)
+    {
+      return String.valueOf(c);
+    }
+
+    String enc = urlEncodings[c];
+    if (enc == null)
+    {
+      try
+      {
+        enc = urlEncodings[c] = URLEncoder.encode(String.valueOf(c),
+                "UTF-8");
+      } catch (UnsupportedEncodingException e)
+      {
+        enc = urlEncodings[c] = String.valueOf(c);
+      }
+    }
+    return enc;
+  }
+
+  public static int firstCharPosIgnoreCase(String text, String chars)
+  {
+    int min = text.length() + 1;
+    for (char c : chars.toLowerCase(Locale.ROOT).toCharArray())
+    {
+      int i = text.toLowerCase(Locale.ROOT).indexOf(c);
+      if (0 <= i && i < min)
+      {
+        min = i;
+      }
+    }
+    return min < text.length() + 1 ? min : -1;
+  }
+
+  public static boolean equalsIgnoreCase(String s1, String s2)
+  {
+    if (s1 == null || s2 == null)
+    {
+      return s1 == s2;
+    }
+    return s1.toLowerCase(Locale.ROOT).equals(s2.toLowerCase(Locale.ROOT));
+  }
+
+  public static int indexOfFirstWhitespace(String text)
+  {
+    int index = -1;
+    Pattern pat = Pattern.compile("\\s");
+    Matcher m = pat.matcher(text);
+    if (m.find())
+    {
+      index = m.start();
+    }
+    return index;
+  }
+
+  /*
+   * implementation of String.replaceLast.
+   * Replaces only the last occurrence of toReplace in string with replacement.
+   */
+  public static String replaceLast(String string, String toReplace,
+          String replacement)
+  {
+    int pos = string.lastIndexOf(toReplace);
+    if (pos > -1)
+    {
+      return new StringBuilder().append(string.substring(0, pos))
+              .append(replacement)
+              .append(string.substring(pos + toReplace.length()))
+              .toString();
+    }
+    else
+    {
+      return string;
+    }
+
+  }
+
+  /* 
+   * return the maximum length of a List of Strings
+   */
+  public static int maxLength(List<String> l)
+  {
+    int max = 0;
+    for (String s : l)
+    {
+      if (s == null)
+        continue;
+      if (s.length() > max)
+        max = s.length();
     }
-    return s.substring(0, 1).toUpperCase() + s.substring(1).toLowerCase();
+    return max;
   }
 }