xapian index format versioning

[sup] / bin / sup-tweak-labels

diff --git a/bin/sup-tweak-labels b/bin/sup-tweak-labels
old mode 100644 (file)
new mode 100755 (executable)
index 0beb77e..8ae5c26
--- a/bin/sup-tweak-labels
+++ b/bin/sup-tweak-labels
@@ -2,6 +2,7 @@
 
 require 'rubygems'
 require 'trollop'
+require 'enumerator'
 require "sup"
 
 class Float
@@ -46,10 +47,12 @@ EOS
 Other options:
 EOS
   opt :verbose, "Print message ids as they're processed."
+  opt :very_verbose, "Print message names and subjects as they're processed."
   opt :all_sources, "Scan over all sources.", :short => :none
   opt :dry_run, "Don't actually modify the index. Probably only useful with --verbose.", :short => "-n"
   opt :version, "Show version information", :short => :none
 end
+opts[:verbose] = true if opts[:very_verbose]
 
 add_labels = (opts[:add] || "").split(",").map { |l| l.intern }.uniq
 remove_labels = (opts[:remove] || "").split(",").map { |l| l.intern }.uniq
@@ -63,10 +66,10 @@ begin
 
   source_ids = 
     if opts[:all_sources]
-      index.sources
+      Redwood::SourceManager.sources
     else
       ARGV.map do |uri|
-        index.source_for uri or Trollop::die "Unknown source: #{uri}. Did you add it with sup-add first?"
+        Redwood::SourceManager.source_for uri or Trollop::die "Unknown source: #{uri}. Did you add it with sup-add first?"
       end
   end.map { |s| s.id }
   Trollop::die "nothing to do: no sources" if source_ids.empty?
@@ -79,19 +82,17 @@ begin
   end
   query += ' ' + opts[:query] if opts[:query]
 
-  qobj, opts = Redwood::Index.parse_user_query_string query
-  query = Redwood::Index.build_query opts.merge(:qobj => qobj)
-
-  results = index.ferret.search query, :limit => :all
-  num_total = results.total_hits
+  parsed_query = index.parse_query query
+  parsed_query.merge! :load_spam => true, :load_deleted => true, :load_killed => true
+  ids = Enumerable::Enumerator.new(index, :each_id, parsed_query).map
+  num_total = ids.size
 
   $stderr.puts "Found #{num_total} documents across #{source_ids.length} sources. Scanning..."
 
   num_changed = num_scanned = 0
   last_info_time = start_time = Time.now
-  results.hits.each do |hit|
+  ids.each do |id|
     num_scanned += 1
-    id = hit.doc
 
     m = index.build_message id
     old_labels = m.labels.clone
@@ -102,7 +103,9 @@ begin
 
     unless m.labels.sort_by { |s| s.to_s } == old_labels.sort_by { |s| s.to_s }
       num_changed += 1
+      puts "From #{m.from}, subject: #{m.subj}" if opts[:very_verbose]
       puts "#{m.id}: {#{old_labels.join ','}} => {#{m.labels.join ','}}" if opts[:verbose]
+      puts if opts[:very_verbose]
       index.sync_message m unless opts[:dry_run]
     end
 
@@ -118,7 +121,7 @@ begin
 
   unless num_changed == 0
     $stderr.puts "Optimizing index..."
-    index.ferret.optimize unless opts[:dry_run]
+    index.optimize unless opts[:dry_run]
   end
 
 rescue Exception => e