lib/sup/util.rb in sup-0.8.1 vs lib/sup/util.rb in sup-0.9

- old
+ new

@@ -1,9 +1,10 @@ require 'thread' require 'lockfile' require 'mime/types' require 'pathname' +require 'set' ## time for some monkeypatching! class Lockfile def gen_lock_id Hash[ @@ -22,10 +23,11 @@ end def lockinfo_on_disk h = load_lock_id IO.read(path) h['mtime'] = File.mtime path + h['path'] = path h end def touch_yourself; touch path end end @@ -88,11 +90,11 @@ end end class Range ## only valid for integer ranges (unless I guess it's exclusive) - def size + def size last - first + (exclude_end? ? 0 : 1) end end class Module @@ -131,23 +133,23 @@ def returning x; yield x; x; end ## clone of java-style whole-method synchronization ## assumes a @mutex variable ## TODO: clean up, try harder to avoid namespace collisions - def synchronized *meth - meth.each do + def synchronized *methods + methods.each do |meth| class_eval <<-EOF alias unsynchronized_#{meth} #{meth} def #{meth}(*a, &b) @mutex.synchronize { unsynchronized_#{meth}(*a, &b) } end EOF end end - def ignore_concurrent_calls *meth - meth.each do + def ignore_concurrent_calls *methods + methods.each do |meth| mutex = "@__concurrent_protector_#{meth}" flag = "@__concurrent_flag_#{meth}" oldmeth = "__unprotected_#{meth}" class_eval <<-EOF alias #{oldmeth} #{meth} @@ -173,11 +175,11 @@ class String ## nasty multibyte hack for ruby 1.8. if it's utf-8, split into chars using ## the utf8 regex and count those. otherwise, use the byte length. def display_length - if $encoding == "UTF-8" + if $encoding == "UTF-8" || $encoding == "utf8" scan(/./u).size else size end end @@ -211,44 +213,44 @@ state = :outstring pos = 0 region_start = 0 while pos <= length newpos = case state - when :escaped_instring, :escaped_outstring: pos + when :escaped_instring, :escaped_outstring then pos else index(/[,"\\]/, pos) - end - + end + if newpos char = self[newpos] else char = nil newpos = length end case char when ?" state = case state - when :outstring: :instring - when :instring: :outstring - when :escaped_instring: :instring - when :escaped_outstring: :outstring + when :outstring then :instring + when :instring then :outstring + when :escaped_instring then :instring + when :escaped_outstring then :outstring end when ?,, nil state = case state - when :outstring, :escaped_outstring: + when :outstring, :escaped_outstring then ret << self[region_start ... newpos].gsub(/^\s+|\s+$/, "") region_start = newpos + 1 :outstring - when :instring: :instring - when :escaped_instring: :instring + when :instring then :instring + when :escaped_instring then :instring end when ?\\ state = case state - when :instring: :escaped_instring - when :outstring: :escaped_outstring - when :escaped_instring: :instring - when :escaped_outstring: :outstring + when :instring then :escaped_instring + when :outstring then :escaped_outstring + when :escaped_instring then :instring + when :escaped_outstring then :outstring end end pos = newpos + 1 end @@ -280,14 +282,22 @@ 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 + unless method_defined? :ord + def ord + self[0] + end + end + + ## takes a 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. + ## + ## split_on will be passed to String#split, so you can leave this nil for space. + def to_set_of_symbols split_on=nil; Set.new split(split_on).map { |x| x.strip.intern } end end class Numeric def clamp min, max if self < min @@ -411,14 +421,10 @@ 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 @@ -488,39 +494,41 @@ end end end end -## simple singleton module. far less complete and insane than the ruby -## standard library one, but automatically forwards methods calls and -## allows for constructors that take arguments. +## simple singleton module. far less complete and insane than the ruby standard +## library one, but it automatically forwards methods calls and allows for +## constructors that take arguments. ## -## You must have #initialize call "self.class.i_am_the_instance self" -## at some point or everything will fail horribly. +## classes that inherit this can define initialize. however, you cannot call +## .new on the class. To get the instance of the class, call .instance; +## to create the instance, call init. module Singleton module ClassMethods def instance; @instance; end def instantiated?; defined?(@instance) && !@instance.nil?; end def deinstantiate!; @instance = nil; end def method_missing meth, *a, &b - raise "no instance defined!" unless defined? @instance + raise "no #{name} instance defined in method call to #{meth}!" unless defined? @instance ## if we've been deinstantiated, just drop all calls. this is ## useful because threads that might be active during the ## cleanup process (e.g. polling) would otherwise have to ## special-case every call to a Singleton object return nil if @instance.nil? @instance.send meth, *a, &b end - def i_am_the_instance o + def init *args raise "there can be only one! (instance)" if defined? @instance - @instance = o + @instance = new(*args) end end def self.included klass + klass.private_class_method :allocate, :new klass.extend ClassMethods end end ## wraps an object. if it throws an exception, keeps a copy. @@ -535,11 +543,11 @@ def clear_error!; @error = nil; end def has_errors?; !@error.nil?; end def method_missing m, *a, &b; __pass m, *a, &b end - + def id; __pass :id; end def to_s; __pass :to_s; end def to_yaml x; __pass :to_yaml, x; end def is_a? c; @o.is_a? c; end @@ -634,20 +642,20 @@ class Iconv def self.easy_decode target, charset, text 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 /iso[-_ ]?8859[-_ ]?15/i: 'ISO-8859-15' - when /unicode[-_ ]1[-_ ]1[-_ ]utf[-_]7/i: "utf-7" + when /UTF[-_ ]?8/i then "utf-8" + when /(iso[-_ ])?latin[-_ ]?1$/i then "ISO-8859-1" + when /iso[-_ ]?8859[-_ ]?15/i then 'ISO-8859-15' + when /unicode[-_ ]1[-_ ]1[-_ ]utf[-_]7/i then "utf-7" else charset end 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]}" + rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::InvalidCharacter, Iconv::IllegalSequence => e + warn "couldn't transcode text from #{charset} to #{target} (\"#{text[0 ... 20]}\"...) (got #{e.message}); using original as is" text end end end