[sup-devel] [PATCH 1/4] dont index redundant data

From: Rich Lane <rlane@club.cc.cmu.edu>
To: sup-devel@rubyforge.org
Subject: [sup-devel] [PATCH 1/4] dont index redundant data
Date: Sat, 16 Jan 2010 12:03:04 -0800	[thread overview]
Message-ID: <1263672187-5174-1-git-send-email-rlane@club.cc.cmu.edu> (raw)

Use the Xapian QueryParser ability to map a prefix in the query to multiple
prefixes in the index. This means we don't need to store duplicate names, email
addresses, and subjects. This also adds the stemmed attachment filenames to the
default (non-prefixed) search. We're storing a subset of the data previous
versions did, so we're able to read them but they can't read us.
---
 lib/sup/xapian_index.rb |   19 ++++++++-----------
 1 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/lib/sup/xapian_index.rb b/lib/sup/xapian_index.rb
index c81dca4..c0b2f9f 100644
--- a/lib/sup/xapian_index.rb
+++ b/lib/sup/xapian_index.rb
@@ -258,9 +258,9 @@ EOS
     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,v| qp.add_prefix k, v }
-    BOOLEAN_PREFIX.each { |k,v| qp.add_boolean_prefix k, v }
-    xapian_query = qp.parse_query(subs, Xapian::QueryParser::FLAG_PHRASE|Xapian::QueryParser::FLAG_BOOLEAN|Xapian::QueryParser::FLAG_LOVEHATE|Xapian::QueryParser::FLAG_WILDCARD, PREFIX['body'])
+    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 } }
+    xapian_query = qp.parse_query(subs, Xapian::QueryParser::FLAG_PHRASE|Xapian::QueryParser::FLAG_BOOLEAN|Xapian::QueryParser::FLAG_LOVEHATE|Xapian::QueryParser::FLAG_WILDCARD)
 
     raise ParseError if xapian_query.nil? or xapian_query.empty?
     query[:qobj] = xapian_query
@@ -276,8 +276,9 @@ EOS
     'body' => 'B',
     'from_name' => 'FN',
     'to_name' => 'TN',
-    'name' => 'N',
+    'name' => %w(FN TN),
     'attachment' => 'A',
+    '' => %w(S B FN TN A),
   }
 
   # Unstemmed
@@ -285,7 +286,7 @@ EOS
     'type' => 'K',
     'from_email' => 'FE',
     'to_email' => 'TE',
-    'email' => 'E',
+    'email' => %w(FE TE),
     'date' => 'D',
     'label' => 'L',
     'source_id' => 'I',
@@ -457,10 +458,8 @@ EOS
     # Person names are indexed with several prefixes
     person_termer = lambda do |d|
       lambda do |p|
-        ["#{d}_name", "name", "body"].each do |x|
-          doc.index_text p.name, PREFIX[x]
-        end if p.name
-        [d, :any].each { |x| doc.add_term mkterm(:email, x, p.email) }
+        doc.index_text p.name, PREFIX["#{d}_name"] if p.name
+        doc.add_term mkterm(:email, d, p.email)
       end
     end
 
@@ -471,7 +470,6 @@ EOS
     subject_text = m.indexable_subject
     body_text = m.indexable_body
     doc.index_text subject_text, PREFIX['subject']
-    doc.index_text subject_text, PREFIX['body']
     doc.index_text body_text, PREFIX['body']
     m.attachments.each { |a| doc.index_text a, PREFIX['attachment'] }
 
@@ -554,7 +552,6 @@ EOS
       case args[0]
       when :from then PREFIX['from_email']
       when :to then PREFIX['to_email']
-      when :any then PREFIX['email']
       else raise "Invalid email term type #{args[0]}"
       end + args[1].to_s.downcase
     when :source_id
-- 
1.6.5.2

_______________________________________________
Sup-devel mailing list
Sup-devel@rubyforge.org
http://rubyforge.org/mailman/listinfo/sup-devel

