require 'trollop'
require "sup"
+PROGRESS_UPDATE_INTERVAL = 15 # seconds
+
class Float
def to_s; sprintf '%.2f', self; end
def to_time_s
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 :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
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
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?"
+ Redwood::SourceManager.source_for uri or Trollop::die "Unknown source: #{uri}. Did you add it with sup-add first?"
end
- sources = index.usual_sources if sources.empty?
- sources = index.sources if opts[:all_sources]
+ sources = Redwood::SourceManager.usual_sources if sources.empty?
+ sources = Redwood::SourceManager.sources if opts[:all_sources]
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
num_added = num_updated = num_scanned = num_restored = 0
last_info_time = start_time = Time.now
- Redwood::PollManager.add_messages_from source, :force_overwrite => true do |m, offset, entry|
+ Redwood::PollManager.add_messages_from source, :force_overwrite => true do |m_old, m, offset|
num_scanned += 1
seen[m.id] = true
+ if Time.now - last_info_time > PROGRESS_UPDATE_INTERVAL
+ last_info_time = Time.now
+ elapsed = last_info_time - start_time
+ start = opts[:start_at] || source.start_offset
+ pctdone = 100.0 * (source.cur_offset - start).to_f / (source.end_offset - start).to_f
+ remaining = (100.0 - pctdone) * (elapsed.to_f / pctdone)
+ $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
+
## 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
+ next if target == :changed && m_old && m_old.source.id == source.id && m_old.source_info == offset
## get the state currently in the index
- index_state = entry[:label].symbolistize if entry
+ index_state = m_old.labels.dup if m_old
## skip if we're operating on restored messages, and this one
## ain't.
## nothin! use default source labels
end
- if Time.now - last_info_time > 60
+ 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"
+ $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
if index_state.nil?
- puts "Adding message #{source}##{offset} with state {#{m.labels * ', '}}" if opts[:verbose]
+ puts "Adding message #{source}##{offset} from #{m.from} 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]
+ puts "Updating message #{source}##{offset}, source #{m_old.source.id} => #{source.id}, offset #{m_old.source_info} => #{offset}, state {#{index_state * ', '}} => {#{m.labels * ', '}}" if opts[:verbose]
num_updated += 1
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
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
projects / sup / blobdiff