## the index structure for redwood. interacts with ferret.
-require 'thread'
require 'fileutils'
require 'ferret'
+begin
+ require 'chronic'
+ $have_chronic = true
+rescue LoadError => e
+ Redwood::log "'chronic' library not found. run 'gem install chronic' to install."
+ $have_chronic = false
+end
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
+ alias ferret 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
@analyzer[:subject] = sa
- @qparser ||= Ferret::QueryParser.new :default_field => :body, :analyzer => @analyzer
+ @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
docid, entry = load_entry_for_id m.id unless docid && entry
raise "no source info for message #{m.id}" unless m.source && m.source_info
- raise "trying deleting non-corresponding entry #{docid}" if docid && @index[docid][:message_id] != m.id
+ raise "trying to delete non-corresponding entry #{docid} with index message-id #{@index[docid][:message_id].inspect} and parameter message id #{m.id.inspect}" if docid && @index[docid][:message_id] != m.id
source_id =
if m.source.is_a? Integer
- raise "Debugging: integer source set"
m.source
else
m.source.id or raise "unregistered source #{m.source} (id #{m.source.id.inspect})"
:date => m.date.to_indexable_s,
:body => m.content,
:snippet => m.snippet,
- :label => m.labels.join(" "),
+ :label => m.labels.uniq.join(" "),
:from => m.from ? m.from.email : "",
:to => (m.to + m.cc + m.bcc).map { |x| x.email }.join(" "),
:subject => wrap_subj(Message.normalize_subj(m.subj)),
docid, entry = load_entry_for_id m.id
## this hasn't been triggered in a long time. TODO: decide whether it's still a problem.
- raise "just added message #{m.id} but couldn't find it in a search" unless docid
+ raise "just added message #{m.id.inspect} 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
## 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.
+ ## only two options, :limit and :skip_killed. if :skip_killed is
+ ## true, 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}"
+ #Redwood::log "Building thread for #{m.id}: #{m.subj}"
messages = {}
searched = {}
num_queries = 0
q.add_query Ferret::Search::TermQuery.new(:message_id, id), :should
q.add_query Ferret::Search::TermQuery.new(:refs, id), :should
- q = build_query :qobj => q, :load_killed => true
+ q = build_query :qobj => q
num_queries += 1
+ killed = false
@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]
+ if @index[docid][:label].split(/\s+/).include?("killed") && opts[:skip_killed]
+ killed = true
+ break
+ end
mid = @index[docid][:message_id]
unless messages.member?(mid)
- Redwood::log "got #{mid} as a child of #{id}"
+ #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 + 1} messages for #{m.id}" if num_queries > 0
- messages.each { |mid, builder| yield mid, builder }
+ if killed
+ Redwood::log "thread for #{m.id} is killed, ignoring"
+ false
+ else
+ Redwood::log "ran #{num_queries} queries to build thread of #{messages.size + 1} messages for #{m.id}: #{m.subj}" if num_queries > 0
+ messages.each { |mid, builder| yield mid, builder }
+ true
+ end
end
## builds a message object from a ferret result
"from" => doc[:from],
"to" => doc[:to],
"message-id" => doc[:message_id],
- "references" => doc[:refs],
+ "references" => doc[:refs].split(/\s+/).map { |x| "<#{x}>" }.join(" "),
}
Message.new :source => source, :source_info => doc[:source_info].to_i,
num = h[:num] || 20
@index.search_each(q, :sort => "date DESC", :limit => :all) do |docid, score|
break if contacts.size >= num
- #Redwood::log "got message with to: #{@index[docid][:to].inspect} and from: #{@index[docid][:from].inspect}"
+ #Redwood::log "got message #{docid} 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
@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
+ ## do any specialized parsing
+ ## returns nil and flashes error message if parsing failed
+ def parse_user_query_string str
+ result = str.gsub(/\b(to|from):(\S+)\b/) do
+ field, name = $1, $2
+ if(p = ContactManager.contact_for(name))
+ [field, p.email]
+ else
+ [field, name]
+ end.join(":")
+ end
+
+ if $have_chronic
+ chronic_failure = false
+ result = result.gsub(/\b(before|on|in|after):(\((.+?)\)\B|(\S+)\b)/) do
+ break if chronic_failure
+ field, datestr = $1, ($3 || $4)
+ realdate = Chronic.parse(datestr, :guess => false)
+ if realdate
+ case field
+ when "after"
+ Redwood::log "chronic: translated #{field}:#{datestr} to #{realdate.end}"
+ "date:(>= #{sprintf "%012d", realdate.end.to_i})"
+ when "before"
+ Redwood::log "chronic: translated #{field}:#{datestr} to #{realdate.begin}"
+ "date:(<= #{sprintf "%012d", realdate.begin.to_i})"
+ else
+ Redwood::log "chronic: translated #{field}:#{datestr} to #{realdate}"
+ "date:(<= #{sprintf "%012d", realdate.end.to_i}) date:(>= #{sprintf "%012d", realdate.begin.to_i})"
+ end
+ else
+ BufferManager.flash "Don't understand date #{datestr.inspect}!"
+ chronic_failure = true
+ end
+ end
+ result = nil if chronic_failure
+ end
+
+ Redwood::log "translated #{str.inspect} to #{result}" unless result == str
+ @qparser.parse result if result
+ end
+
def build_query opts
query = Ferret::Search::BooleanQuery.new
query.add_query opts[:qobj], :must if opts[:qobj]
query.add_query Ferret::Search::TermQuery.new("label", "spam"), :must_not unless opts[:load_spam] || labels.include?(:spam)
query.add_query Ferret::Search::TermQuery.new("label", "deleted"), :must_not unless opts[:load_deleted] || labels.include?(:deleted)
- query.add_query Ferret::Search::TermQuery.new("label", "killed"), :must_not unless opts[:load_killed] || labels.include?(:killed)
+ query.add_query Ferret::Search::TermQuery.new("label", "killed"), :must_not if opts[:skip_killed]
query
end
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