X-Git-Url: https://git.cworth.org/git?a=blobdiff_plain;f=bin%2Fsup-sync;h=b743c1c13e3cdf9f73d6d24a5c88882985c30681;hb=ac2d27b230c0afc36eafddec1c387a6ab68a837d;hp=611afc4c6ccdfbd42120fcd7071216ac98fc72aa;hpb=f2e3351e55e177818eab5c2e2099548b638111f4;p=sup

diff --git a/bin/sup-sync b/bin/sup-sync
old mode 100644
new mode 100755
index 611afc4..b743c1c
--- a/bin/sup-sync
+++ b/bin/sup-sync
@@ -5,11 +5,11 @@ require 'rubygems'
 require 'trollop'
 require "sup"
 
+PROGRESS_UPDATE_INTERVAL = 15 # seconds
+
 class Float
   def to_s; sprintf '%.2f', self; end
-   def to_time_s
-     infinite? ? "unknown" : super
-   end
+  def to_time_s; infinite? ? "unknown" : super end
 end
 
 class Numeric
@@ -19,6 +19,10 @@ class Numeric
   end
 end
 
+class Set
+  def to_s; to_a * ',' end
+end
+
 def time
   startt = Time.now
   yield
@@ -52,10 +56,10 @@ by running "sup-add --help".
 Options controlling WHICH messages sup-sync operates on:
 EOS
   opt :new, "Operate on new messages only. Don't scan over the entire source. (Default.)", :short => :none
-  opt :changed, "Scan over the entire source for messages that have been deleted, altered, or moved from another source. (In the case of mbox sources, this includes all messages AFTER an altered message.)"
+  opt :changed, "Scan over the entire source for messages that have been deleted, altered, or moved from another source."
   opt :restored, "Operate only on those messages included in a dump file as specified by --restore which have changed state."
   opt :all, "Operate on all messages in the source, regardless of newness or changedness."
-  opt :start_at, "For --changed and --all, start at a particular offset.", :type => :int
+  opt :start_at, "For --changed, --restored and --all, start at a particular offset.", :type => :int
 
 text <<EOS
 
@@ -66,7 +70,7 @@ EOS
   opt :discard, "Discard any message state in the index and use the default source state. Dangerous!", :short => :none
   opt :archive, "When using the default source state, mark messages as archived.", :short => "-x"
   opt :read, "When using the default source state, mark messages as read."
-  opt :extra_labels, "When using the default source state, also apply these user-defined labels. Should be a comma-separated list.", :type => String, :short => :none
+  opt :extra_labels, "When using the default source state, also apply these user-defined labels (a comma-separated list)", :default => "", :short => :none
 
 text <<EOS
 
@@ -84,142 +88,156 @@ end
 Trollop::die :restored, "requires --restore" if opts[:restored] unless opts[:restore]
 if opts[:start_at]
   Trollop::die :start_at, "must be non-negative" if opts[:start_at] < 0
-  Trollop::die :start_at, "requires either --changed or --all" unless opts[:changed] || opts[:all]
+  Trollop::die :start_at, "requires either --changed, --restored or --all" unless opts[:changed] || opts[:restored] || opts[:all]
 end
 
 target = [:new, :changed, :all, :restored].find { |x| opts[x] } || :new
 op = [:asis, :restore, :discard].find { |x| opts[x] } || :asis
 
 Redwood::start
-index = Redwood::Index.new
-
-restored_state =
-  if opts[:restore]
-    dump = {}
-    $stderr.puts "Loading state dump from #{opts[:restore]}..."
-    IO.foreach opts[:restore] do |l|
-      l =~ /^(\S+) \((.*?)\)$/ or raise "Can't read dump line: #{l.inspect}"
-      mid, labels = $1, $2
-      dump[mid] = labels.split(" ").map { |x| x.intern }
-    end
-    $stderr.puts "Read #{dump.size} entries from dump file."
-    dump
-  else
-    {}
+index = Redwood::Index.init
+
+restored_state = if opts[:restore]
+  dump = {}
+  $stderr.puts "Loading state dump from #{opts[:restore]}..."
+  IO.foreach opts[:restore] do |l|
+    l =~ /^(\S+) \((.*?)\)$/ or raise "Can't read dump line: #{l.inspect}"
+    mid, labels = $1, $2
+    dump[mid] = labels.to_set_of_symbols
   end
+  $stderr.puts "Read #{dump.size} entries from dump file."
+  dump
+else
+  {}
+end
 
 seen = {}
 index.lock_or_die
 begin
   index.load
 
-  sources = ARGV.map do |uri|
-    index.source_for uri or Trollop::die "Unknown source: #{uri}. Did you add it with sup-add first?"
+  sources = if opts[:all_sources]
+    Redwood::SourceManager.sources
+  elsif ARGV.empty?
+    Redwood::SourceManager.usual_sources
+  else
+    ARGV.map do |uri|
+      Redwood::SourceManager.source_for uri or Trollop::die "Unknown source: #{uri}. Did you add it with sup-add first?"
+    end
   end
-  
-  sources = index.usual_sources if sources.empty?
-  sources = index.sources if opts[:all_sources]
 
+  ## for all target specifications except for only-new messages, reset the
+  ## source to the beginning (or to the user-specified starting point.)
   unless target == :new
     if opts[:start_at]
-      sources.each { |s| s.seek_to! opts[:start_at] }
+      Trollop::die :start_at, "can only be used on one source" unless sources.size == 1
+      sources.first.seek_to! opts[:start_at]
+      sources.first.correct_offset! if sources.first.respond_to?(:correct_offset!)
     else
       sources.each { |s| s.reset! }
     end
   end
-  
+
   sources.each do |source|
     $stderr.puts "Scanning #{source}..."
     num_added = num_updated = num_scanned = num_restored = 0
     last_info_time = start_time = Time.now
 
-    Redwood::PollManager.add_messages_from source do |m, offset, entry|
+    Redwood::PollManager.each_message_from source do |m|
       num_scanned += 1
       seen[m.id] = true
+      old_m = index.build_message m.id
+
+      case target
+      when :changed
+        ## skip this message if we're operating only on changed messages, the
+        ## message is in the index, and it's unchanged from what the source is
+        ## reporting.
+        next if old_m && old_m.source.id == m.source.id && old_m.source_info == m.source_info
+      when :restored
+        ## skip if we're operating on restored messages, and this one
+        ## ain't (or we wouldn't be making a change)
+        next unless old_m && restored_state[m.id] && restored_state[m.id] != old_m.labels
+      when :new
+        ## nothing to do; we'll consider all messages starting at the start offset, which
+        ## hasn't been changed.
+      when :all
+        ## nothing to do; we'll consider all messages starting at the start offset, which
+        ## was reset to the beginning above.
+      end
 
-      ## skip if we're operating only on changed messages, the message
-      ## is in the index, and it's unchanged from what the source is
-      ## reporting.
-      next if target == :changed && entry && entry[:source_id].to_i == source.id && entry[:source_info].to_i == offset
-
-      ## get the state currently in the index
-      index_state =
-        if entry
-          entry[:label].split(/\s+/).map { |x| x.intern }
+      ## tweak source labels according to commandline arguments if necessary
+      m.labels.delete :inbox if opts[:archive]
+      m.labels.delete :unread if opts[:read]
+      m.labels += opts[:extra_labels].to_set_of_symbols(",")
+
+      ## decide what to do based on message labels and the operation we're performing
+      dothis, new_labels = case
+      when (op == :restore) && restored_state[m.id] && old_m && (old_m.labels != restored_state[m.id])
+        [:update_message_state, restored_state[m.id]]
+      when op == :discard
+        if old_m && (old_m.labels != m.labels)
+          [:update_message_state, m.labels]
         else
-          nil
+          # don't do anything
         end
-
-      ## skip if we're operating on restored messages, and this one
-      ## ain't.
-      next if target == :restored && (!restored_state[m.id] || (index_state && restored_state[m.id].sort_by { |s| s.to_s } == index_state.sort_by { |s| s.to_s }))
-
-      ## m.labels is the default source labels. tweak these according
-      ## to default source state modification flags.
-      m.labels -= [:inbox] if opts[:archive]
-      m.labels -= [:unread] if opts[:read]
-      m.labels += opts[:extra_labels].split(/\s*,\s*/).map { |x| x.intern } if opts[:extra_labels]
-
-      ## assign message labels based on the operation we're performing
-      case op
-      when :asis
-        m.labels = index_state if index_state
-      when :restore
-        ## if the entry exists on disk
-        if restored_state[m.id]
-          m.labels = restored_state[m.id]
-          num_restored += 1
-        elsif index_state
-          m.labels = index_state
+      else
+        ## duplicate behavior of poll mode: if index_state is non-nil, this is a newer
+        ## version of an older message, so merge in any new labels except :unread and
+        ## :inbox.
+        ##
+        ## TODO: refactor such that this isn't duplicated
+        if old_m
+          m.labels = old_m.labels + (m.labels - [:unread, :inbox])
+          :update_message
+        else
+          :add_message
         end
-      when :discard
-        ## nothin! use default source labels
       end
 
-      if Time.now - last_info_time > 60
+      ## now, actually do the operation
+      case dothis
+      when :add_message
+        $stderr.puts "Adding new message #{source}###{m.source_info} with labels #{m.labels}" if opts[:verbose]
+        index.add_message m unless opts[:dry_run]
+        num_added += 1
+      when :update_message
+        $stderr.puts "Updating message #{source}###{m.source_info}; labels #{old_m.labels} => #{m.labels}; offset #{old_m.source_info} => #{m.source_info}" if opts[:verbose]
+        index.update_message m unless opts[:dry_run]
+        num_updated += 1
+      when :update_message_state
+        $stderr.puts "Changing flags for #{source}##{m.source_info} from #{m.labels} to #{new_labels}"
+        m.labels = new_labels
+        index.update_message_state m unless opts[:dry_run]
+        num_updated += 1
+      end
+
+      if Time.now - last_info_time > PROGRESS_UPDATE_INTERVAL
         last_info_time = Time.now
         elapsed = last_info_time - start_time
         pctdone = source.respond_to?(:pct_done) ? source.pct_done : 100.0 * (source.cur_offset.to_f - source.start_offset).to_f / (source.end_offset - source.start_offset).to_f
         remaining = (100.0 - pctdone) * (elapsed.to_f / pctdone)
-        $stderr.puts "## #{num_scanned} (#{pctdone}%) read; #{elapsed.to_time_s} elapsed; #{remaining.to_time_s} remaining"
-      end
-
-      if index_state.nil?
-        puts "Adding message #{source}##{offset} with state {#{m.labels * ', '}}" if opts[:verbose]
-        num_added += 1
-      else
-        puts "Updating message #{source}##{offset}, source #{entry[:source_id]} => #{source.id}, offset #{entry[:source_info]} => #{offset}, state {#{index_state * ', '}} => {#{m.labels * ', '}}" if opts[:verbose]
-        num_updated += 1
+        $stderr.printf "## read %dm (about %.0f%%) @ %.1fm/s. %s elapsed, about %s remaining\n", num_scanned, pctdone, num_scanned / elapsed, elapsed.to_time_s, remaining.to_time_s
       end
-
-      opts[:dry_run] ? nil : m
     end
+
     $stderr.puts "Scanned #{num_scanned}, added #{num_added}, updated #{num_updated} messages from #{source}."
     $stderr.puts "Restored state on #{num_restored} (#{100.0 * num_restored / num_scanned}%) messages." if num_restored > 0
   end
 
   ## delete any messages in the index that claim they're from one of
   ## these sources, but that we didn't see.
-  ##
-  ## kinda crappy code here, because we delve directly into the Ferret
-  ## API.
-  ##
-  ## TODO: move this to Index, i suppose.
-
-
-  if target == :all || target == :changed
+  if (target == :all || target == :changed)
     $stderr.puts "Deleting missing messages from the index..."
     num_del, num_scanned = 0, 0
     sources.each do |source|
       raise "no source id for #{source}" unless source.id
-      q = "+source_id:#{source.id}"
-      q += " +source_info: >= #{opts[:start_at]}" if opts[:start_at]
-      index.index.search_each(q, :limit => :all) do |docid, score|
+      index.each_message :source_id => source.id, :load_spam => true, :load_deleted => true, :load_killed => true do |m|
         num_scanned += 1
-        mid = index.index[docid][:message_id]
-        unless seen[mid]
-          puts "Deleting #{mid}" if opts[:verbose]
-          index.index.delete docid unless opts[:dry_run]
+        unless seen[m.id]
+          next unless m.source_info >= opts[:start_at] if opts[:start_at]
+          puts "Deleting #{m.id}" if opts[:verbose]
+          index.delete m.id unless opts[:dry_run]
           num_del += 1
         end
       end
@@ -227,9 +245,11 @@ begin
     $stderr.puts "Deleted #{num_del} / #{num_scanned} messages"
   end
 
+  index.save
+
   if opts[:optimize]
     $stderr.puts "Optimizing index..."
-    optt = time { index.index.optimize unless opts[:dry_run] }
+    optt = time { index.optimize unless opts[:dry_run] }
     $stderr.puts "Optimized index of size #{index.size} in #{optt}s."
   end
 rescue Redwood::FatalSourceError => e
@@ -238,7 +258,6 @@ rescue Exception => e
   File.open("sup-exception-log.txt", "w") { |f| f.puts e.backtrace }
   raise
 ensure
-  #index.save # actually, don't want to save!
   Redwood::finish
   index.unlock
 end