index.rb in sup-0.1

- old
+ new

@@ -5,27 +5,100 @@
 require 'ferret'
 
 module Redwood
 
 class Index
+  class LockError < StandardError
+    def initialize h
+      @h = h
+    end
+
+    def method_missing m; @h[m.to_s] end
+  end
+
   include Singleton
 
   attr_reader :index
   def initialize dir=BASE_DIR
     @dir = dir
     @sources = {}
     @sources_dirty = false
 
     wsa = Ferret::Analysis::WhiteSpaceAnalyzer.new false
-    sa = Ferret::Analysis::StandardAnalyzer.new Ferret::Analysis::FULL_ENGLISH_STOP_WORDS, true
+    sa = Ferret::Analysis::StandardAnalyzer.new [], true
     @analyzer = Ferret::Analysis::PerFieldAnalyzer.new wsa
     @analyzer[:body] = sa
-    @qparser ||= Ferret::QueryParser.new :default_field => :body, :analyzer => @analyzer
+    @analyzer[:subject] = sa
+    @qparser ||= Ferret::QueryParser.new :default_field => :body, :analyzer => @analyzer, :or_default => false
+    @lock = Lockfile.new lockfile, :retries => 0, :max_age => nil
 
     self.class.i_am_the_instance self
   end
 
+  def lockfile; File.join @dir, "lock" end
+
+  def lock
+    Redwood::log "locking #{lockfile}..."
+    begin
+      @lock.lock
+    rescue Lockfile::MaxTriesLockError
+      raise LockError, @lock.lockinfo_on_disk
+    end
+  end
+
+  def start_lock_update_thread
+    @lock_update_thread = Redwood::reporting_thread do
+      while true
+        sleep 30
+        @lock.touch_yourself
+      end
+    end
+  end
+
+  def stop_lock_update_thread
+    @lock_update_thread.kill if @lock_update_thread
+    @lock_update_thread = nil
+  end
+
+  def fancy_lock_error_message_for e
+    secs = Time.now - e.mtime
+    mins = secs.to_i / 60
+    time =
+      if mins == 0
+        "#{secs.to_i} seconds"
+      else
+        "#{mins} minutes"
+      end
+
+    <<EOS
+Error: the sup index is locked by another process! User '#{e.user}' on
+host '#{e.host}' is running #{e.pname} with pid #{e.pid}. The process was alive
+as of #{time} ago.
+EOS
+  end
+
+  def lock_or_die
+    begin
+      lock
+    rescue LockError => e
+      $stderr.puts fancy_lock_error_message_for(e)
+      $stderr.puts <<EOS
+
+You can wait for the process to finish, or, if it crashed and left a
+stale lock file behind, you can manually delete #{@lock.path}.
+EOS
+      exit
+    end
+  end
+
+  def unlock
+    if @lock && @lock.locked?
+      Redwood::log "unlocking #{lockfile}..."
+      @lock.unlock
+    end
+  end
+
   def load
     load_sources
     load_index
   end
 
@@ -114,11 +187,11 @@
     raise "just added message #{m.id} but couldn't find it in a search" unless docid
     true
   end
 
   def save_index fn=File.join(@dir, "ferret")
-    # don't have to do anything,  apparently
+    # don't have to do anything, apparently
   end
 
   def contains_id? id
     @index.search(Ferret::Search::TermQuery.new(:message_id, id)).total_hits > 0
   end
@@ -141,29 +214,29 @@
     end
   end
 
   def num_results_for opts={}
     return 0 if @index.size == 0 # otherwise ferret barfs ###TODO: remove this once my ferret patch is accepted
+
     q = build_query opts
-    index.search(q).total_hits
+    index.search(q, :limit => 1).total_hits
   end
 
   ## yield all messages in the thread containing 'm' by repeatedly
-  ## querying the index. uields pairs of message ids and
+  ## querying the index. yields pairs of message ids and
   ## message-building lambdas, so that building an unwanted message
   ## can be skipped in the block if desired.
   ##
   ## stops loading any thread if a message with a :killed flag is found.
-
   SAME_SUBJECT_DATE_LIMIT = 7
   def each_message_in_thread_for m, opts={}
+    Redwood::log "Building thread for #{m.id}: #{m.subj}"
     messages = {}
     searched = {}
     num_queries = 0
 
-    ## todo: make subject querying configurable
-    if true # do subject queries
+    if $config[:thread_by_subject] # do subject queries
       date_min = m.date - (SAME_SUBJECT_DATE_LIMIT * 12 * 3600)
       date_max = m.date + (SAME_SUBJECT_DATE_LIMIT * 12 * 3600)
 
       q = Ferret::Search::BooleanQuery.new true
       sq = Ferret::Search::PhraseQuery.new(:subject)
@@ -194,18 +267,19 @@
       num_queries += 1
       @index.search_each(q, :limit => :all) do |docid, score|
         break if opts[:limit] && messages.size >= opts[:limit]
         break if @index[docid][:label].split(/\s+/).include? "killed" unless opts[:load_killed]
         mid = @index[docid][:message_id]
-        unless messages.member? mid
+        unless messages.member?(mid)
+          Redwood::log "got #{mid} as a child of #{id}"
           messages[mid] ||= lambda { build_message docid }
           refs = @index[docid][:refs].split(" ")
           pending += refs
         end
       end
     end
-    Redwood::log "ran #{num_queries} queries to build thread of #{messages.size} messages for #{m.id}" if num_queries > 0
+    Redwood::log "ran #{num_queries} queries to build thread of #{messages.size + 1} messages for #{m.id}" if num_queries > 0
     messages.each { |mid, builder| yield mid, builder }
   end
 
   ## builds a message object from a ferret result
   def build_message docid
@@ -259,15 +333,13 @@
       #Redwood::log "got message with to: #{@index[docid][:to].inspect} and from: #{@index[docid][:from].inspect}"
       f = @index[docid][:from]
       t = @index[docid][:to]
 
       if AccountManager.is_account_email? f
-        t.split(" ").each { |e| #Redwood::log "adding #{e} because there's a message to him from account email #{f}"; 
-          contacts[Person.for(e)] = true }
+        t.split(" ").each { |e| contacts[PersonManager.person_for(e)] = true }
       else
-        #Redwood::log "adding from #{f} because there's a message from him to #{t}"
-        contacts[Person.for(f)] = true
+        contacts[PersonManager.person_for(f)] = true
       end
     end
 
     contacts.keys.compact
   end
@@ -276,10 +348,17 @@
     source_array = (Redwood::load_yaml_obj(fn) || []).map { |o| Recoverable.new o }
     @sources = Hash[*(source_array).map { |s| [s.id, s] }.flatten]
     @sources_dirty = false
   end
 
+  def has_any_from_source_with_label? source, label
+    q = Ferret::Search::BooleanQuery.new
+    q.add_query Ferret::Search::TermQuery.new("source_id", source.id.to_s), :must
+    q.add_query Ferret::Search::TermQuery.new("label", label.to_s), :must
+    index.search(q, :limit => 1).total_hits > 0
+  end
+
 protected
 
   def parse_user_query_string str; @qparser.parse str; end
   def build_query opts
     query = Ferret::Search::BooleanQuery.new
@@ -304,12 +383,12 @@
   def save_sources fn=Redwood::SOURCE_FN
     if @sources_dirty || @sources.any? { |id, s| s.dirty? }
       bakfn = fn + ".bak"
       if File.exists? fn
         File.chmod 0600, fn
-        FileUtils.mv fn, bakfn, :force => true unless File.exists?(bakfn) && File.size(bakfn) > File.size(fn)
+        FileUtils.mv fn, bakfn, :force => true unless File.exists?(bakfn) && File.size(fn) == 0
       end
-      Redwood::save_yaml_obj @sources.values, fn
+      Redwood::save_yaml_obj @sources.values.sort_by { |s| s.id.to_i }, fn, true
       File.chmod 0600, fn
     end
     @sources_dirty = false
   end
 end