index.rb in sup-0.13.0

- old
+ new

@@ -11,19 +11,22 @@
 rescue LoadError => e
   debug "No 'chronic' gem detected. Install it for date/time query restrictions."
   $have_chronic = false
 end
 
+if ([Xapian.major_version, Xapian.minor_version, Xapian.revision] <=> [1,2,1]) < 0
+	fail "Xapian version 1.2.1 or higher required"
+end
+
 module Redwood
 
 # This index implementation uses Xapian for searching and storage. It
 # tends to be slightly faster than Ferret for indexing and significantly faster
 # for searching due to precomputing thread membership.
 class Index
   include InteractiveLock
 
-  STEM_LANGUAGE = "english"
   INDEX_VERSION = '4'
 
   ## dates are converted to integers for xapian, and are used for document ids,
   ## so we must ensure they're reasonably valid. this typically only affect
   ## spam.
@@ -204,11 +207,13 @@
 
     m = Message.new :locations => locations,
                     :labels => entry[:labels],
                     :snippet => entry[:snippet]
 
-    mk_person = lambda { |x| Person.new(*x.reverse!) }
+    # Try to find person from contacts before falling back to
+    # generating it from the address.
+    mk_person = lambda { |x| Person.from_name_and_email(*x.reverse!) }
     entry[:from] = mk_person[entry[:from]]
     entry[:to].map!(&mk_person)
     entry[:cc].map!(&mk_person)
     entry[:bcc].map!(&mk_person)
 
@@ -229,11 +234,11 @@
     each_id_by_date :participants => email_addresses do |id,b|
       break if contacts.size >= num
       m = b.call
       ([m.from]+m.to+m.cc+m.bcc).compact.each { |p| contacts << [p.name, p.email] }
     end
-    contacts.to_a.compact.map { |n,e| Person.new n, e }[0...num]
+    contacts.to_a.compact[0...num].map { |n,e| Person.from_name_and_email n, e }
   end
 
   ## Yield each message-id matching query
   EACH_ID_PAGE = 100
   def each_id query={}
@@ -420,16 +425,16 @@
 
     debug "translated query: #{subs.inspect}"
 
     qp = Xapian::QueryParser.new
     qp.database = @xapian
-    qp.stemmer = Xapian::Stem.new(STEM_LANGUAGE)
+    qp.stemmer = Xapian::Stem.new($config[:stem_language])
     qp.stemming_strategy = Xapian::QueryParser::STEM_SOME
     qp.default_op = Xapian::Query::OP_AND
     qp.add_valuerangeprocessor(Xapian::NumberValueRangeProcessor.new(DATE_VALUENO, 'date:', true))
-    NORMAL_PREFIX.each { |k,vs| vs.each { |v| qp.add_prefix k, v } }
-    BOOLEAN_PREFIX.each { |k,vs| vs.each { |v| qp.add_boolean_prefix k, v } }
+    NORMAL_PREFIX.each { |k,info| info[:prefix].each { |v| qp.add_prefix k, v } }
+    BOOLEAN_PREFIX.each { |k,info| info[:prefix].each { |v| qp.add_boolean_prefix k, v, info[:exclusive] } }
 
     begin
       xapian_query = qp.parse_query(subs, Xapian::QueryParser::FLAG_PHRASE|Xapian::QueryParser::FLAG_BOOLEAN|Xapian::QueryParser::FLAG_LOVEHATE|Xapian::QueryParser::FLAG_WILDCARD)
     rescue RuntimeError => e
       raise ParseError, "xapian query parser error: #{e}"
@@ -476,35 +481,35 @@
 
   private
 
   # Stemmed
   NORMAL_PREFIX = {
-    'subject' => 'S',
-    'body' => 'B',
-    'from_name' => 'FN',
-    'to_name' => 'TN',
-    'name' => %w(FN TN),
-    'attachment' => 'A',
-    'email_text' => 'E',
-    '' => %w(S B FN TN A E),
+    'subject' => {:prefix => 'S', :exclusive => false},
+    'body' => {:prefix => 'B', :exclusive => false},
+    'from_name' => {:prefix => 'FN', :exclusive => false},
+    'to_name' => {:prefix => 'TN', :exclusive => false},
+    'name' => {:prefix => %w(FN TN), :exclusive => false},
+    'attachment' => {:prefix => 'A', :exclusive => false},
+    'email_text' => {:prefix => 'E', :exclusive => false},
+    '' => {:prefix => %w(S B FN TN A E), :exclusive => false},
   }
 
   # Unstemmed
   BOOLEAN_PREFIX = {
-    'type' => 'K',
-    'from_email' => 'FE',
-    'to_email' => 'TE',
-    'email' => %w(FE TE),
-    'date' => 'D',
-    'label' => 'L',
-    'source_id' => 'I',
-    'attachment_extension' => 'O',
-    'msgid' => 'Q',
-    'id' => 'Q',
-    'thread' => 'H',
-    'ref' => 'R',
-    'location' => 'J',
+    'type' => {:prefix => 'K', :exclusive => true},
+    'from_email' => {:prefix => 'FE', :exclusive => false},
+    'to_email' => {:prefix => 'TE', :exclusive => false},
+    'email' => {:prefix => %w(FE TE), :exclusive => false},
+    'date' => {:prefix => 'D', :exclusive => true},
+    'label' => {:prefix => 'L', :exclusive => false},
+    'source_id' => {:prefix => 'I', :exclusive => true},
+    'attachment_extension' => {:prefix => 'O', :exclusive => false},
+    'msgid' => {:prefix => 'Q', :exclusive => true},
+    'id' => {:prefix => 'Q', :exclusive => true},
+    'thread' => {:prefix => 'H', :exclusive => false},
+    'ref' => {:prefix => 'R', :exclusive => false},
+    'location' => {:prefix => 'J', :exclusive => false},
   }
 
   PREFIX = NORMAL_PREFIX.merge BOOLEAN_PREFIX
 
   MSGID_VALUENO = 0
@@ -666,25 +671,25 @@
   ## Index content that can't be changed by the user
   def index_message_static m, doc, entry
     # Person names are indexed with several prefixes
     person_termer = lambda do |d|
       lambda do |p|
-        doc.index_text p.name, PREFIX["#{d}_name"] if p.name
-        doc.index_text p.email, PREFIX['email_text']
+        doc.index_text p.name, PREFIX["#{d}_name"][:prefix] if p.name
+        doc.index_text p.email, PREFIX['email_text'][:prefix]
         doc.add_term mkterm(:email, d, p.email)
       end
     end
 
     person_termer[:from][m.from] if m.from
     (m.to+m.cc+m.bcc).each(&(person_termer[:to]))
 
     # Full text search content
     subject_text = m.indexable_subject
     body_text = m.indexable_body
-    doc.index_text subject_text, PREFIX['subject']
-    doc.index_text body_text, PREFIX['body']
-    m.attachments.each { |a| doc.index_text a, PREFIX['attachment'] }
+    doc.index_text subject_text, PREFIX['subject'][:prefix]
+    doc.index_text body_text, PREFIX['body'][:prefix]
+    m.attachments.each { |a| doc.index_text a, PREFIX['attachment'][:prefix] }
 
     # Miscellaneous terms
     doc.add_term mkterm(:date, m.date) if m.date
     doc.add_term mkterm(:type, 'mail')
     doc.add_term mkterm(:msgid, m.id)
@@ -758,29 +763,29 @@
 
   # Construct a Xapian term
   def mkterm type, *args
     case type
     when :label
-      PREFIX['label'] + args[0].to_s.downcase
+      PREFIX['label'][:prefix] + args[0].to_s.downcase
     when :type
-      PREFIX['type'] + args[0].to_s.downcase
+      PREFIX['type'][:prefix] + args[0].to_s.downcase
     when :date
-      PREFIX['date'] + args[0].getutc.strftime("%Y%m%d%H%M%S")
+      PREFIX['date'][:prefix] + args[0].getutc.strftime("%Y%m%d%H%M%S")
     when :email
       case args[0]
-      when :from then PREFIX['from_email']
-      when :to then PREFIX['to_email']
+      when :from then PREFIX['from_email'][:prefix]
+      when :to then PREFIX['to_email'][:prefix]
       else raise "Invalid email term type #{args[0]}"
       end + args[1].to_s.downcase
     when :source_id
-      PREFIX['source_id'] + args[0].to_s.downcase
+      PREFIX['source_id'][:prefix] + args[0].to_s.downcase
     when :location
-      PREFIX['location'] + [args[0]].pack('n') + args[1].to_s
+      PREFIX['location'][:prefix] + [args[0]].pack('n') + args[1].to_s
     when :attachment_extension
-      PREFIX['attachment_extension'] + args[0].to_s.downcase
+      PREFIX['attachment_extension'][:prefix] + args[0].to_s.downcase
     when :msgid, :ref, :thread
-      PREFIX[type.to_s] + args[0][0...(MAX_TERM_LENGTH-1)]
+      PREFIX[type.to_s][:prefix] + args[0][0...(MAX_TERM_LENGTH-1)]
     else
       raise "Invalid term type #{type}"
     end
   end
 end
@@ -796,10 +801,10 @@
     self.data = Marshal.dump x
   end
 
   def index_text text, prefix, weight=1
     term_generator = Xapian::TermGenerator.new
-    term_generator.stemmer = Xapian::Stem.new(Redwood::Index::STEM_LANGUAGE)
+    term_generator.stemmer = Xapian::Stem.new($config[:stem_language])
     term_generator.document = self
     term_generator.index_text text, weight, prefix
   end
 
   alias old_add_term add_term