root/lang/ruby/mdmaildir/mdd.rb @ 9074

#!/usr/local/bin/ruby
# $Id$

#
# = Manipulates message-digest file for whole of messages in the Maildir.
#
# Authors::  $Author: genta $
# Revision:: $Revision: 77 $
#
class MDDigest
  require 'gdbm'
  require 'digest/sha1'
  require 'pp'

  attr_reader :path, :basedir, :db

  # Create MDDigest instance.  MDDigest opens a message-digest file in
  # the specified Maildir.  The message-digest file is stored into the
  # top-level directory as filename like "_maildir_/mddigest".
  #
  # _maildir_:: Path of Maildir.
  # returns::   An instance of MDDigest class
  def initialize(maildir)
    @basedir = maildir.dup
    @path = File.join(@basedir, 'mddigest')
    open()
  end

  def open;  @db = GDBM.open(@path); end
  private :open

  # Close the backend DBM. Call this method at the end of your program.
  def close;
    @db.reorganize.close
  end

  # Truncate message-digest file.
  def clear
    @db.clear
  end

  # Caliculates a message-digest for specified message, and records it
  # into message-digest file. 
  #
  # _path_::  Relative path of a message from Maildir directory.
  # returns:: void
  def add(path)
    apath = abspath(path)

    md = hash(apath).hexdigest
    size = File.size(apath)
    key = md + '|' + size.to_s

    if @db.key?(key) then
      merge(key, path)
      return
    end
    @db[key] = path
  end

  # Check specified key and file are already records in message-digest
  # file, or not.
  #
  # _key_::   Key of file-hash. It typically message-digest + size of
  #           message.
  # _file_::  Relative path of a message from Maildir directory.
  # returns:: *true* if it already exists.
  #           *false* for not exists.
  def has_file?(key, file)
    return false if @db[key].nil?
    @db[key].split('\0').each do |src|
      return true if src == file
    end
    return false
  end

  # Wrapper of GDBM#each. It is for traversal all of messages in Maildir
  # by using a message-digest file.
  def each(&block)
    @db.each(&block)
  end


  private

  # Caliculates a Message digest for specified message.
  #
  # _file_::  Path for a message.
  # returns:: Instance of Digest::SHA1.
  def hash(file)
    md = Digest::SHA1.new
    File.open(file, 'r') do |fd|
      buf = ''
      while fd.read(256, buf)
        md << buf
      end
    end
    return md
  end

  # _key_::
  # _dest_::
  def merge(key, dest)
    dfolder = folder(abspath(dest))
    list = @db[key].split('\0')
    list.map! do |src|
      return if src == dest
      if folder(src) == dfolder then
        return if File.mtime(abspath(dest)) < File.mtime(abspath(src))
        next
      end
      src
    end.compact!
    list += [dest]
    raise "Idential" if list.join('\0') == @db[key]
    @db[key] = list.join('\0')
  end

  # Determines a folder name for a specified message.
  #
  # _path_::  Relative path of a message from Maildir directory
  # returns:: A folder name in Maildir for a message that directed by path.
  def folder(path)
    f, = path.split('/')
    return '' unless f =~ /^\./
    return f
  end

  # Convert relative path to the absolute path. The root of absolute path is
  # Maildir directory.
  #
  # _file_::  Relative path from Maildir directory.
  # returns:: Absolute path that converted from _file_.
  def abspath(file)
    File.expand_path(file, @basedir)
  end
end