ruby--ruby/lib/find.rb

#
# find.rb: the Find module for processing all files under a given directory.
#

#
# The +Find+ module supports the top-down traversal of a set of file paths.
#
# For example, to total the size of all files under your home directory,
# ignoring anything in a "dot" directory (e.g. $HOME/.ssh):
#
#   require 'find'
#
#   total_size = 0
#
#   Find.find(ENV["HOME"]) do |path|
#     if FileTest.directory?(path)
#       if File.basename(path)[0] == ?.
#         Find.prune       # Don't look any further into this directory.
#       else
#         next
#       end
#     else
#       total_size += FileTest.size(path)
#     end
#   end
#
module Find

  #
  # Calls the associated block with the name of every file and directory listed
  # as arguments, then recursively on their subdirectories, and so on.
  #
  # Returns an enumerator if no block is given.
  #
  # See the +Find+ module documentation for an example.
  #
  def find(*paths) # :yield: path
    block_given? or return enum_for(__method__, *paths)

    fs_encoding = Encoding.find("filesystem")

    paths.collect!{|d| raise Errno::ENOENT unless File.exist?(d); d.dup}.each do |path|
      enc = path.encoding == Encoding::US_ASCII ? fs_encoding : path.encoding
      ps = [path]
      while file = ps.shift
        catch(:prune) do
          yield file.dup.taint
          begin
            s = File.lstat(file)
          rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
            next
          end
          if s.directory? then
            begin
              fs = Dir.entries(file, encoding: enc)
            rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
              next
            end
            fs.sort!
            fs.reverse_each {|f|
              next if f == "." or f == ".."
              f = File.join(file, f)
              ps.unshift f.untaint
            }
          end
        end
      end
    end
    nil
  end

  #
  # Skips the current file or directory, restarting the loop with the next
  # entry. If the current file is a directory, that directory will not be
  # recursively entered. Meaningful only within the block associated with
  # Find::find.
  #
  # See the +Find+ module documentation for an example.
  #
  def prune
    throw :prune
  end

  module_function :find, :prune
end