summaryrefslogtreecommitdiff
path: root/lib/feed2imap/cache.rb
blob: 006e99e35b39b5ad6503bc07531d066810d0838b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
=begin
Feed2Imap - RSS/Atom Aggregator uploading to an IMAP Server
Copyright (c) 2005 Lucas Nussbaum <lucas@lucas-nussbaum.net>

This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
=end

# This class manages a cache of items
# (items which have already been seen)

require 'digest/md5'

class ItemCache
  def initialize
    @channels = {}
    @@cacheidx = 0
    self
  end

  # Returns the really new items amongst items
  def get_new_items(id, items)
    @channels[id] ||= CachedChannel::new
    return @channels[id].get_new_items(items)
  end

  # Commit changes to the cache
  def commit_cache(id)
    @channels[id] ||= CachedChannel::new
    @channels[id].commit
  end

  # Get the last time the cache was updated
  def get_last_check(id)
    @channels[id] ||= CachedChannel::new
    @channels[id].lastcheck
  end

  # Get the last time the cache was updated
  def set_last_check(id, time)
    @channels[id] ||= CachedChannel::new
    @channels[id].lastcheck = time
    self
  end

  # Load the cache from an IO stream
  def load(io)
    begin
      @@cacheidx, @channels = Marshal.load(io)
    rescue
      @channels = Marshal.load(io)
      @@cacheidx = 0
    end
  end

  # Save the cache to an IO stream
  def save(io)
    Marshal.dump([@@cacheidx, @channels], io)
  end
  
  # Return the number of channels in the cache
  def nbchannels
    @channels.length
  end

  # Return the number of items in the cache
  def nbitems
    nb = 0
    @channels.each_value { |c|
      nb += c.nbitems
    }
    nb
  end

  def ItemCache.getindex
    i = @@cacheidx
    @@cacheidx += 1
    i
  end
end

class CachedChannel
  # Size of the cache for each feed
  CACHESIZE = 50

  attr_accessor :lastcheck, :items

  def initialize
    @lastcheck = Time::at(0)
    @items = []
    @itemstemp = [] # see below
    @nbnewitems = 0
  end

  # Let's explain @items and @itemstemp.
  # @items contains the CachedItems serialized to the disk cache.
  # The - quite complicated - get_new_items method fills in @itemstemp
  # but leaves @items unchanged.
  # Later, the commit() method replaces @items with @itemstemp and
  # empties @itemstemp. This way, if something wrong happens during the
  # upload to the IMAP server, items aren't lost.
  # @nbnewitems is set by get_new_items, and is used to limit the number
  # of (old) items serialized.

  UPDATEDDEBUG = false

  # Returns the really new items amongst items
  def get_new_items(items)
    # save number of new items
    @nbnewitems = items.length
    # set items' cached version if not set yet
    newitems = []
    updateditems = []
    @itemstemp = @items
    items.each { |i| i.cacheditem ||= CachedItem::new(i) }
    # remove dups
    dups = true
    while dups
      dups = false
      for i in 0...items.length do
        for j in i+1...items.length do
          if items[i].cacheditem.link == items[j].cacheditem.link
            if UPDATEDDEBUG
              puts "## Removed #{items[j].cacheditem.to_s}"
            end
            items.delete_at(j)
            dups = true
            break
          end
        end
        break if dups
      end
    end
    # debug : dump interesting info to stdout.
    if UPDATEDDEBUG
      puts "-------Items downloaded :----------"
      items.each { |i| puts "#{i.cacheditem.to_s}" }
      puts "-------Items already there :----------"
      @items.each { |i| puts "#{i.to_s}" }
    end
    items.each do |i|
      found = false
      # Try to find a perfect match
      @items.each do |j|
        if i.cacheditem == j
          i.cacheditem.index = j.index
          found = true
          # let's put j in front of itemstemp
          @itemstemp.delete(j)
          @itemstemp.unshift(j)
          break
        end
      end
      next if found
      # Try to find an updated item
      @items.each do |j|
        # Do we need a better heuristic ?
        if i.link and i.link == j.link
          i.cacheditem.index = j.index
          i.cacheditem.updated = true
          updateditems.push(i)
          found = true
          # let's put j in front of itemstemp
          @itemstemp.delete(j)
          @itemstemp.unshift(i.cacheditem)
          break
        end
      end
      next if found
      # add as new
      i.cacheditem.create_index
      newitems.push(i)
      # add i.cacheditem to @itemstemp
      @itemstemp.unshift(i.cacheditem)
    end
    if UPDATEDDEBUG
      puts "-------New items :----------"
      newitems.each { |i| puts "#{i.cacheditem.to_s}" }
      puts "-------Updated items :----------"
      updateditems.each { |i| puts "#{i.cacheditem.to_s}" }
    end
    return [newitems, updateditems]
  end
  
  def commit
    # too old items must be dropped
    n = @nbnewitems > CACHESIZE ? @nbnewitems : CACHESIZE
    @items = @itemstemp[0..n]
    @itemstemp = []
    self
  end

  # returns the number of items
  def nbitems
    @items.length
  end
end

# This class is the only thing kept in the cache
class CachedItem
  attr_reader :title, :link, :hash
  attr_accessor :index
  attr_accessor :updated

  def initialize(item)
    @title = item.title
    @link = item.link
    if item.content.nil?
      @hash = nil
    else
      @hash = Digest::MD5.hexdigest(item.content.to_s)
    end
  end

  def ==(other)
    @title == other.title and @link == other.link and @hash == other.hash
  end

  def create_index
    @index = ItemCache.getindex
  end

  def to_s
    "\"#{@title}\" #{@link} #{@hash}"
  end
end