lib/sup/util.rb in sup-0.7 vs lib/sup/util.rb in sup-0.8

@@ -170,10 +170,12 @@
     end
   end
 end
 
 class String
+  def display_length; scan(/./u).size end
+
   def camel_to_hyphy
     self.gsub(/([a-z])([A-Z0-9])/, '\1-\2').downcase
   end
 
   def find_all_positions x
@@ -186,15 +188,10 @@
       start = pos + 1
     end
     ret
   end
 
-  ## one of the few things i miss from perl
-  def ucfirst
-    self[0 .. 0].upcase + self[1 .. -1]
-  end
-
   ## a very complicated regex found on teh internets to split on
   ## commas, unless they occurr within double quotes.
   def split_on_commas
     split(/,\s*(?=(?:[^"]*"[^"]*")*(?![^"]*"))/)
   end
@@ -274,10 +271,15 @@
   end
 
   def normalize_whitespace
     gsub(/\t/, "    ").gsub(/\r/, "")
   end
+
+  ## takes a space-separated list of words, and returns an array of symbols.
+  ## typically used in Sup for translating Ferret's representation of a list
+  ## of labels (a string) to an array of label symbols.
+  def symbolistize; split.map { |x| x.intern } end
 end
 
 class Numeric
   def clamp min, max
     if self < min
@@ -401,10 +403,14 @@
 
   def to_boolean_h; Hash[*map { |x| [x, true] }.flatten]; end
 
   def last= e; self[-1] = e end
   def nonempty?; !empty? end
+
+  def to_set_of_symbols
+    map { |x| x.is_a?(Symbol) ? x : x.intern }.uniq
+  end
 end
 
 class Time
   def to_indexable_s
     sprintf "%012d", self
@@ -618,19 +624,22 @@
   end
 end
 
 class Iconv
   def self.easy_decode target, charset, text
-    return text if charset =~ /^(x-unknown|unknown[-_]?8bit|ascii[-_]?7[-_]?bit)$/i
+    return text if charset =~ /^(x-unknown|unknown[-_ ]?8bit|ascii[-_ ]?7[-_ ]?bit)$/i
     charset = case charset
-                when /UTF[-_]?8/i: "utf-8"
-                when /(iso[-_])?latin[-_]?1$/i: "ISO-8859-1"
-                when /unicode[-_]1[-_]1[-_]utf[-_]7/i: "utf-7"
-                else charset
-              end
+      when /UTF[-_ ]?8/i: "utf-8"
+      when /(iso[-_ ])?latin[-_ ]?1$/i: "ISO-8859-1"
+      when /iso[-_ ]?8859[-_ ]?15/i: 'ISO-8859-15'
+      when /unicode[-_ ]1[-_ ]1[-_ ]utf[-_]7/i: "utf-7"
+      else charset
+    end
 
-    # Convert:
-    #
-    # Remember - Iconv.open(to, from)!
-    Iconv.iconv(target + "//IGNORE", charset, text + " ").join[0 .. -2]
+    begin
+      Iconv.iconv(target + "//IGNORE", charset, text + " ").join[0 .. -2]
+    rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::IllegalSequence => e
+      Redwood::log "warning: error (#{e.class.name}) decoding text from #{charset} to #{target}: #{text[0 ... 20]}"
+      text
+    end
   end
 end