+require 'thread'
require 'lockfile'
require 'mime/types'
require 'pathname'
+require 'set'
## time for some monkeypatching!
class Lockfile
def lockinfo_on_disk
h = load_lock_id IO.read(path)
h['mtime'] = File.mtime path
+ h['path'] = path
h
end
rescue SystemCallError
return "?"
end
-
- if s < 1024
- s.to_s + "b"
- elsif s < (1024 * 1024)
- (s / 1024).to_s + "k"
- elsif s < (1024 * 1024 * 1024)
- (s / 1024 / 1024).to_s + "m"
- else
- (s / 1024 / 1024 / 1024).to_s + "g"
- end
+ s.to_human_size
end
def human_time
class EncodingUnsupportedError < StandardError; end
class Message
- def add_file_attachment fn
+ def self.make_file_attachment fn
bfn = File.basename fn
- a = Message.new
t = MIME::Types.type_for(bfn).first || MIME::Types.type_for("exe").first
+ make_attachment IO.read(fn), t.content_type, t.encoding, bfn.to_s
+ end
+
+ def charset
+ if header.field?("content-type") && header.fetch("content-type") =~ /charset="?(.*?)"?(;|$)/i
+ $1
+ end
+ end
- a.header.add "Content-Disposition", "attachment; filename=#{bfn.to_s.inspect}"
- a.header.add "Content-Type", "#{t.content_type}; name=#{bfn.to_s.inspect}"
- a.header.add "Content-Transfer-Encoding", t.encoding
+ def self.make_attachment payload, mime_type, encoding, filename
+ a = Message.new
+ a.header.add "Content-Disposition", "attachment; filename=#{filename.inspect}"
+ a.header.add "Content-Type", "#{mime_type}; name=#{filename.inspect}"
+ a.header.add "Content-Transfer-Encoding", encoding if encoding
a.body =
- case t.encoding
+ case encoding
when "base64"
- [IO.read(fn)].pack "m"
+ [payload].pack "m"
when "quoted-printable"
- [IO.read(fn)].pack "M"
- when "7bit", "8bit"
- IO.read(fn)
+ [payload].pack "M"
+ when "7bit", "8bit", nil
+ payload
else
- raise EncodingUnsupportedError, t.encoding
+ raise EncodingUnsupportedError, encoding.inspect
end
-
- add_part a
- end
-
- def charset
- if header.field?("content-type") && header.fetch("content-type") =~ /charset="?(.*?)"?(;|$)/
- $1
- end
+ a
end
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
def defer_all_other_method_calls_to obj
class_eval %{
def method_missing meth, *a, &b; @#{obj}.send meth, *a, &b; end
- def respond_to? meth; @#{obj}.respond_to?(meth); end
+ def respond_to?(m, include_private = false)
+ @#{obj}.respond_to?(m, include_private)
+ end
}
end
end
## clone of java-style whole-method synchronization
## assumes a @mutex variable
- def synchronized *meth
- meth.each do
+ ## TODO: clean up, try harder to avoid namespace collisions
+ def synchronized *methods
+ methods.each do |meth|
class_eval <<-EOF
alias unsynchronized_#{meth} #{meth}
def #{meth}(*a, &b)
EOF
end
end
+
+ 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}
+ def #{meth}(*a, &b)
+ #{mutex} = Mutex.new unless defined? #{mutex}
+ #{flag} = true unless defined? #{flag}
+ run = #{mutex}.synchronize do
+ if #{flag}
+ #{flag} = false
+ true
+ end
+ end
+ if run
+ ret = #{oldmeth}(*a, &b)
+ #{mutex}.synchronize { #{flag} = true }
+ ret
+ end
+ end
+ EOF
+ end
+ end
end
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" || $encoding == "utf8"
+ scan(/./u).size
+ else
+ size
+ end
+ end
+
def camel_to_hyphy
self.gsub(/([a-z])([A-Z0-9])/, '\1-\2').downcase
end
ret
end
- def ucfirst
- self[0 .. 0].upcase + self[1 .. -1]
- end
-
## a very complicated regex found on teh internets to split on
## commas, unless they occurr within double quotes.
def split_on_commas
split(/,\s*(?=(?:[^"]*"[^"]*")*(?![^"]*"))/)
end
+ ## ok, here we do it the hard way. got to have a remainder for purposes of
+ ## tab-completing full email addresses
+ def split_on_commas_with_remainder
+ ret = []
+ state = :outstring
+ pos = 0
+ region_start = 0
+ while pos <= length
+ newpos = case state
+ when :escaped_instring, :escaped_outstring then pos
+ else index(/[,"\\]/, pos)
+ end
+
+ if newpos
+ char = self[newpos]
+ else
+ char = nil
+ newpos = length
+ end
+
+ case char
+ when ?"
+ state = case state
+ when :outstring then :instring
+ when :instring then :outstring
+ when :escaped_instring then :instring
+ when :escaped_outstring then :outstring
+ end
+ when ?,, nil
+ state = case state
+ when :outstring, :escaped_outstring then
+ ret << self[region_start ... newpos].gsub(/^\s+|\s+$/, "")
+ region_start = newpos + 1
+ :outstring
+ when :instring then :instring
+ when :escaped_instring then :instring
+ end
+ when ?\\
+ state = case state
+ 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
+
+ remainder = case state
+ when :instring
+ self[region_start .. -1].gsub(/^\s+/, "")
+ else
+ nil
+ end
+
+ [ret, remainder]
+ end
+
def wrap len
ret = []
s = self
def normalize_whitespace
gsub(/\t/, " ").gsub(/\r/, "")
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
end
def in? range; range.member? self; end
+
+ def to_human_size
+ if self < 1024
+ to_s + "b"
+ elsif self < (1024 * 1024)
+ (self / 1024).to_s + "k"
+ elsif self < (1024 * 1024 * 1024)
+ (self / 1024 / 1024).to_s + "m"
+ else
+ (self / 1024 / 1024 / 1024).to_s + "g"
+ end
+ end
end
class Fixnum
- def num_digits base=10
- return 1 if self == 0
- 1 + (Math.log(self) / Math.log(10)).floor
- end
-
def to_character
if self < 128 && self >= 0
chr
"<#{self}>"
end
end
+
+ ## hacking the english language
+ def pluralize s
+ to_s + " " +
+ if self == 1
+ s
+ else
+ if s =~ /(.*)y$/
+ $1 + "ies"
+ else
+ s + "s"
+ end
+ end
+ end
end
class Hash
def to_boolean_h; Hash[*map { |x| [x, true] }.flatten]; end
def last= e; self[-1] = e end
+ def nonempty?; !empty? end
end
class Time
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
@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, and
-## rethrows it for any further method calls.
+## wraps an object. if it throws an exception, keeps a copy.
class Recoverable
def initialize o
@o = o
- @e = nil
+ @error = nil
+ @mutex = Mutex.new
end
- def clear_error!; @e = nil; end
- def has_errors?; !@e.nil?; end
- def error; @e; end
+ attr_accessor :error
+
+ def clear_error!; @error = nil; end
+ def has_errors?; !@error.nil?; end
+
+ def method_missing m, *a, &b; __pass m, *a, &b 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
- def respond_to? m; @o.respond_to? m end
+ def respond_to?(m, include_private=false)
+ @o.respond_to?(m, include_private)
+ end
def __pass m, *a, &b
begin
@o.send(m, *a, &b)
rescue Exception => e
- @e = e
- raise e
+ @error ||= e
+ raise
end
end
end
defer_all_other_method_calls_to :hash
end
+
+class OrderedHash < Hash
+ alias_method :store, :[]=
+ alias_method :each_pair, :each
+ attr_reader :keys
+
+ def initialize *a
+ @keys = []
+ a.each { |k, v| self[k] = v }
+ end
+
+ def []= key, val
+ @keys << key unless member?(key)
+ super
+ end
+
+ def values; keys.map { |k| self[k] } end
+ def index key; @keys.index key end
+
+ def delete key
+ @keys.delete key
+ super
+ end
+
+ def each; @keys.each { |k| yield k, self[k] } end
+end
+
+## easy thread-safe class for determining who's the "winner" in a race (i.e.
+## first person to hit the finish line
+class FinishLine
+ def initialize
+ @m = Mutex.new
+ @over = false
+ end
+
+ def winner?
+ @m.synchronize { !@over && @over = true }
+ end
+end
+
+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 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::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