lib/sup/index.rb in sup-0.0.7 vs lib/sup/index.rb in sup-0.0.8

- old
+ new

@@ -28,10 +28,11 @@ load_sources load_index end def save + Redwood::log "saving index and sources..." FileUtils.mkdir_p @dir unless File.exists? @dir save_sources save_index end @@ -70,29 +71,50 @@ field_infos.create_index dir @index = Ferret::Index::Index.new(:path => dir, :analyzer => @analyzer) end end - ## Update the message state on disk, by deleting and re-adding it. - ## The message must exist in the index. docid and entry are found - ## unless given. + ## Syncs the message to the index: deleting if it's already there, + ## and adding either way. Index state will be determined by m.labels. ## - ## Overwrites the labels on disk with the new labels in 'm', so that - ## we can actually change message state. - def update_message m, docid=nil, entry=nil - unless docid && entry - docid, entry = load_entry_for_id m.id - raise ArgumentError, "cannot find #{m.id} in the index" unless entry - end + ## docid and entry can be specified if they're already known. + def sync_message m, docid=nil, entry=nil + docid, entry = load_entry_for_id m.id unless docid && entry - raise "no entry and no source info for message #{m.id}" unless m.source && m.source_info + 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 "deleting non-corresponding entry #{docid}" unless @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})" + end - @index.delete docid - add_message m + to = (m.to + m.cc + m.bcc).map { |x| x.email }.join(" ") + d = { + :message_id => m.id, + :source_id => source_id, + :source_info => m.source_info, + :date => m.date.to_indexable_s, + :body => m.content, + :snippet => m.snippet, + :label => m.labels.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)), + :refs => (m.refs + m.replytos).uniq.join(" "), + } + + @index.delete docid if docid + @index.add_document d + 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 + true end def save_index fn=File.join(@dir, "ferret") # don't have to do anything, apparently end @@ -208,45 +230,10 @@ def fresh_thread_id; @next_thread_id += 1; end def wrap_subj subj; "__START_SUBJECT__ #{subj} __END_SUBJECT__"; end def unwrap_subj subj; subj =~ /__START_SUBJECT__ (.*?) __END_SUBJECT__/ && $1; end - ## Adds a message to the index. The message cannot already exist in - ## the index. - def add_message m - raise ArgumentError, "index already contains #{m.id}" if contains? m - - source_id = - if m.source.is_a? Integer - m.source - else - m.source.id or raise "unregistered source #{m.source} (id #{m.source.id.inspect})" - end - - to = (m.to + m.cc + m.bcc).map { |x| x.email }.join(" ") - d = { - :message_id => m.id, - :source_id => source_id, - :source_info => m.source_info, - :date => m.date.to_indexable_s, - :body => m.content, - :snippet => m.snippet, - :label => m.labels.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)), - :refs => (m.refs + m.replytos).uniq.join(" "), - } - - @index.add_document d - - 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 - true - end - def drop_entry docno; @index.delete docno; end def load_entry_for_id mid results = @index.search(Ferret::Search::TermQuery.new(:message_id, mid)) return if results.total_hits == 0 @@ -283,10 +270,16 @@ end contacts.keys.compact end + def load_sources fn=Redwood::SOURCE_FN + 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 + protected def parse_user_query_string str; @qparser.parse str; end def build_query opts query = Ferret::Search::BooleanQuery.new @@ -304,14 +297,9 @@ 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 - end - - def load_sources fn=Redwood::SOURCE_FN - @sources = Hash[*(Redwood::load_yaml_obj(fn) || []).map { |s| [s.id, s] }.flatten] - @sources_dirty = false end def save_sources fn=Redwood::SOURCE_FN if @sources_dirty || @sources.any? { |id, s| s.dirty? } bakfn = fn + ".bak"