add hooks for before- and after- yaml marshalling

[sup] / lib / sup / xapian_index.rb

diff --git a/lib/sup/xapian_index.rb b/lib/sup/xapian_index.rb
index 6358a20ca4a463682597199ec94acb5ae0e3b374..f79b05503f914d7b3c28dd3d030615402847d88d 100644 (file)
--- a/lib/sup/xapian_index.rb
+++ b/lib/sup/xapian_index.rb
@@ -20,14 +20,16 @@ class XapianIndex < BaseIndex
     super
 
     @index_mutex = Monitor.new
+  end
 
-    @entries = MarshalledGDBM.new File.join(dir, "entries.db")
-    @docids = MarshalledGDBM.new File.join(dir, "docids.db")
-    @thread_members = MarshalledGDBM.new File.join(dir, "thread_members.db")
-    @thread_ids = MarshalledGDBM.new File.join(dir, "thread_ids.db")
-    @assigned_docids = GDBM.new File.join(dir, "assigned_docids.db")
+  def load_index
+    @entries = MarshalledGDBM.new File.join(@dir, "entries.db")
+    @docids = MarshalledGDBM.new File.join(@dir, "docids.db")
+    @thread_members = MarshalledGDBM.new File.join(@dir, "thread_members.db")
+    @thread_ids = MarshalledGDBM.new File.join(@dir, "thread_ids.db")
+    @assigned_docids = GDBM.new File.join(@dir, "assigned_docids.db")
 
-    @xapian = Xapian::WritableDatabase.new(File.join(dir, "xapian"), Xapian::DB_CREATE_OR_OPEN)
+    @xapian = Xapian::WritableDatabase.new(File.join(@dir, "xapian"), Xapian::DB_CREATE_OR_OPEN)
     @term_generator = Xapian::TermGenerator.new()
     @term_generator.stemmer = Xapian::Stem.new(STEM_LANGUAGE)
     @enquire = Xapian::Enquire.new @xapian
@@ -35,9 +37,6 @@ class XapianIndex < BaseIndex
     @enquire.docid_order = Xapian::Enquire::ASCENDING
   end
 
-  def load_index
-  end
-
   def save_index
   end
 
@@ -88,6 +87,10 @@ class XapianIndex < BaseIndex
       m
   end
 
+  def add_message m; sync_message m end
+  def update_message m; sync_message m end
+  def update_message_state m; sync_message m end
+
   def sync_message m, opts={}
     entry = synchronize { @entries[m.id] }
     snippet = m.snippet
@@ -101,7 +104,7 @@ class XapianIndex < BaseIndex
       :source_info => m.source_info,
       :date => (entry[:date] || m.date),
       :snippet => snippet,
-      :labels => labels.uniq,
+      :labels => labels,
       :from => (entry[:from] || [m.from.email, m.from.name]),
       :to => (entry[:to] || m.to.map { |p| [p.email, p.name] }),
       :cc => (entry[:cc] || m.cc.map { |p| [p.email, p.name] }),
@@ -111,7 +114,7 @@ class XapianIndex < BaseIndex
       :replytos => (entry[:replytos] || m.replytos),
     }
 
-    m.labels.each { |l| LabelManager << l }
+    labels.each { |l| LabelManager << l }
 
     synchronize do
       index_message m, opts
@@ -120,6 +123,7 @@ class XapianIndex < BaseIndex
     end
     true
   end
+  private :sync_message
 
   def num_results_for query={}
     xapian_query = build_xapian_query query
@@ -304,6 +308,8 @@ class XapianIndex < BaseIndex
 
   DATE_VALUENO = 0
 
+  MAX_TERM_LENGTH = 245
+
   # Xapian can very efficiently sort in ascending docid order. Sup always wants
   # to sort by descending date, so this method maps between them. In order to
   # handle multiple messages per second, we use a logistic curve centered
@@ -428,7 +434,7 @@ class XapianIndex < BaseIndex
 
     @term_generator.document = doc
     text.each { |text,prefix| @term_generator.index_text text, 1, prefix }
-    terms.each { |term| doc.add_term term }
+    terms.each { |term| doc.add_term term if term.length <= MAX_TERM_LENGTH }
     doc.add_value DATE_VALUENO, date_value
     doc.data = m.id