bugfix: index label parsing code incorrect

Apparently split(/\s+/) is significantly different from split (which is
equivalent to split(" ")) in at least one case:

>> " a b  c   ".split(/\s+/)
=> ["", "a", "b", "c"]
>> " a b  c   ".split
=> ["a", "b", "c"]

This patch refactors the majority of uses of split(/\s+/) to a String#symbolize
method, which is correct.

diff --git a/bin/sup-sync b/bin/sup-sync
index 91710d47495ab263a69e03ec709657d1ee8b66ae..fe729533033068288b0d90662ccca161c7f32a1c 100644 (file)
--- a/bin/sup-sync
+++ b/bin/sup-sync
@@ -100,7 +100,7 @@ restored_state =
     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 }
+      dump[mid] = labels.symbolistize
     end
     $stderr.puts "Read #{dump.size} entries from dump file."
     dump
@@ -143,7 +143,7 @@ begin
       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 = entry[:label].split(/\s+/).map { |x| x.intern } if entry
+      index_state = entry[:label].symbolistize if entry
 
       ## skip if we're operating on restored messages, and this one
       ## ain't.
@@ -153,7 +153,7 @@ begin
       ## 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]
+      m.labels += opts[:extra_labels].strip.split(/\s*,\s*/).map { |x| x.intern } if opts[:extra_labels]
 
       ## assign message labels based on the operation we're performing
       case op

diff --git a/bin/sup-sync-back b/bin/sup-sync-back
index 4216cf9e46f5db3c595b72edb8462f15bb0fe966..4f1387e7f1e62d9ec13c03833d0670c9e87e4531 100644 (file)
--- a/bin/sup-sync-back
+++ b/bin/sup-sync-back
@@ -109,7 +109,7 @@ EOS
       num_scanned += 1
 
       if entry
-        labels = entry[:label].split.map { |x| x.intern }.to_boolean_h
+        labels = entry[:label].symbolistize.to_boolean_h
 
         if labels.member? :deleted
           if opts[:drop_deleted]

diff --git a/lib/sup/buffer.rb b/lib/sup/buffer.rb
index c9e34b3595c62b82b64350163e0d547e127f95eb..2db6aa8e8e2e5ada1232b34271504ca553a4bfc4 100644 (file)
--- a/lib/sup/buffer.rb
+++ b/lib/sup/buffer.rb
@@ -484,7 +484,7 @@ EOS
 
     return unless answer
 
-    user_labels = answer.split(/\s+/).map { |l| l.intern }
+    user_labels = answer.symbolistize
     user_labels.each do |l|
       if forbidden_labels.include?(l) || LabelManager::RESERVED_LABELS.include?(l)
         BufferManager.flash "'#{l}' is a reserved label!"

diff --git a/lib/sup/index.rb b/lib/sup/index.rb
index 838d601347f1f86ffba21ac72e37c3e191ac95ba..2bdf22b0c2b2ea22f904cc349672a1fe69fc20ad 100644 (file)
--- a/lib/sup/index.rb
+++ b/lib/sup/index.rb
@@ -226,7 +226,7 @@ EOS
     ## but merge in the labels.
     if entry[:source_id] && entry[:source_info] && entry[:label] &&
       ((entry[:source_id].to_i > source_id) || (entry[:source_info].to_i < m.source_info))
-      labels = (entry[:label].split(/\s+/).map { |l| l.intern } + m.labels).uniq
+      labels = (entry[:label].symbolistize + m.labels).uniq
       #Redwood::log "found updated version of message #{m.id}: #{m.subj}"
       #Redwood::log "previous version was at #{entry[:source_id].inspect}:#{entry[:source_info].inspect}, this version at #{source_id.inspect}:#{m.source_info.inspect}"
       #Redwood::log "merged labels are #{labels.inspect} (index #{entry[:label].inspect}, message #{m.labels.inspect})"
@@ -415,7 +415,7 @@ EOS
       }
 
       Message.new :source => source, :source_info => doc[:source_info].to_i,
-                  :labels => doc[:label].split(" ").map { |s| s.intern },
+                  :labels => doc[:label].symbolistize,
                   :snippet => doc[:snippet], :header => fake_header
     end
   end

diff --git a/lib/sup/poll.rb b/lib/sup/poll.rb
index 5027218c49d66318b309a062c1d222d81699d3a1..8c10ef1734084539e8dd59a9aba829034bfba0d4 100644 (file)
--- a/lib/sup/poll.rb
+++ b/lib/sup/poll.rb
@@ -97,7 +97,7 @@ EOS
         numi = 0
         add_messages_from source do |m, offset, entry|
           ## always preserve the labels on disk.
-          m.labels = ((m.labels - [:unread, :inbox]) + entry[:label].split(/\s+/).map { |x| x.intern }).uniq if entry
+          m.labels = ((m.labels - [:unread, :inbox]) + entry[:label].symbolistize).uniq if entry
           yield "Found message at #{offset} with labels {#{m.labels * ', '}}"
           unless entry
             num += 1

diff --git a/lib/sup/util.rb b/lib/sup/util.rb
index 8b92fd2e079761965d3684ab051aee1b72cf6840..c54a2c0db2b47efdc547000cc0ed9f8974536960 100644 (file)
--- a/lib/sup/util.rb
+++ b/lib/sup/util.rb
@@ -271,6 +271,11 @@ class String
   def normalize_whitespace
     gsub(/\t/, "    ").gsub(/\r/, "")
   end
+
+  ## takes a space-separated list of words, and returns an array of symbols.
+  ## typically used in Sup for translating Ferret's representation of a list
+  ## of labels (a string) to an array of label symbols.
+  def symbolistize; split.map { |x| x.intern } end
 end
 
 class Numeric