X-Git-Url: https://git.cworth.org/git?a=blobdiff_plain;f=lib%2Fsup%2Findex.rb;h=ca01ee76cc89c118933c5122b616b4b6f45a59bb;hb=0b5543a02c5d2dfc1a725e63e4a922bea9f903fd;hp=2bdf22b0c2b2ea22f904cc349672a1fe69fc20ad;hpb=4ea04212928446fb62c5fd5ecca9c18b0339edf9;p=sup

diff --git a/lib/sup/index.rb b/lib/sup/index.rb
index 2bdf22b..ca01ee7 100644
--- a/lib/sup/index.rb
+++ b/lib/sup/index.rb
@@ -2,7 +2,6 @@
 
 require 'fileutils'
 require 'ferret'
-require 'fastthread'
 
 begin
   require 'chronic'
@@ -177,31 +176,31 @@ EOS
     end
   end
 
-  ## Syncs the message to the index: deleting if it's already there,
-  ## and adding either way. Index state will be determined by m.labels.
+  ## Syncs the message to the index, replacing any previous version.  adding
+  ## either way. Index state will be determined by the message's #labels
+  ## accessor.
   ##
-  ## docid and entry can be specified if they're already known.
-  def sync_message m, docid=nil, entry=nil, opts={}
-    docid, entry = load_entry_for_id m.id unless docid && entry
+  ## if need_load is false, docid and entry are assumed to be set to the
+  ## result of load_entry_for_id (which can be nil).
+  def sync_message m, need_load=true, docid=nil, entry=nil, opts={}
+    docid, entry = load_entry_for_id m.id if need_load
 
     raise "no source info for message #{m.id}" unless m.source && m.source_info
     @index_mutex.synchronize do
       raise "trying to delete non-corresponding entry #{docid} with index message-id #{@index[docid][:message_id].inspect} and parameter message id #{m.id.inspect}" if docid && @index[docid][:message_id] != m.id
     end
 
-    source_id = 
-      if m.source.is_a? Integer
-        m.source
-      else
-        m.source.id or raise "unregistered source #{m.source} (id #{m.source.id.inspect})"
-      end
+    source_id = if m.source.is_a? Integer
+      m.source
+    else
+      m.source.id or raise "unregistered source #{m.source} (id #{m.source.id.inspect})"
+    end
 
-    snippet = 
-      if m.snippet_contains_encrypted_content? && $config[:discard_snippets_from_encrypted_messages]
-        ""
-      else
-        m.snippet
-      end
+    snippet = if m.snippet_contains_encrypted_content? && $config[:discard_snippets_from_encrypted_messages]
+      ""
+    else
+      m.snippet
+    end
 
     ## write the new document to the index. if the entry already exists in the
     ## index, reuse it (which avoids having to reload the entry from the source,
@@ -261,15 +260,14 @@ EOS
       :refs => (entry[:refs] || (m.refs + m.replytos).uniq.join(" ")),
     }
 
-    @index_mutex.synchronize  do
+    @index_mutex.synchronize do
       @index.delete docid if docid
       @index.add_document d
     end
 
-    docid, entry = load_entry_for_id m.id
-    ## this hasn't been triggered in a long time. TODO: decide whether it's still a problem.
-    raise "just added message #{m.id.inspect} but couldn't find it in a search" unless docid
-    true
+    ## this hasn't been triggered in a long time.
+    ## docid, entry = load_entry_for_id m.id
+    ## raise "just added message #{m.id.inspect} but couldn't find it in a search" unless docid
   end
 
   def save_index fn=File.join(@dir, "ferret")
@@ -333,7 +331,7 @@ EOS
 
       q = Ferret::Search::BooleanQuery.new true
       sq = Ferret::Search::PhraseQuery.new(:subject)
-      wrap_subj(Message.normalize_subj(m.subj)).split(/\s+/).each do |t|
+      wrap_subj(Message.normalize_subj(m.subj)).split.each do |t|
         sq.add_term t
       end
       q.add_query sq, :must
@@ -378,7 +376,7 @@ EOS
           unless messages.member?(mid)
             #Redwood::log "got #{mid} as a child of #{id}"
             messages[mid] ||= lambda { build_message docid }
-            refs = @index[docid][:refs].split(" ")
+            refs = @index[docid][:refs].split
             pending += refs.select { |id| !searched[id] }
           end
         end
@@ -389,7 +387,7 @@ EOS
       Redwood::log "thread for #{m.id} is killed, ignoring"
       false
     else
-      Redwood::log "ran #{num_queries} queries to build thread of #{messages.size + 1} messages for #{m.id}: #{m.subj}" if num_queries > 0
+      Redwood::log "ran #{num_queries} queries to build thread of #{messages.size} messages for #{m.id}: #{m.subj}" if num_queries > 0
       messages.each { |mid, builder| yield mid, builder }
       true
     end
@@ -409,14 +407,16 @@ EOS
         "date" => Time.at(doc[:date].to_i),
         "subject" => unwrap_subj(doc[:subject]),
         "from" => doc[:from],
-        "to" => doc[:to].split(/\s+/).join(", "), # reformat
+        "to" => doc[:to].split.join(", "), # reformat
         "message-id" => doc[:message_id],
-        "references" => doc[:refs].split(/\s+/).map { |x| "<#{x}>" }.join(" "),
+        "references" => doc[:refs].split.map { |x| "<#{x}>" }.join(" "),
       }
 
-      Message.new :source => source, :source_info => doc[:source_info].to_i,
+      m = Message.new :source => source, :source_info => doc[:source_info].to_i,
                   :labels => doc[:label].symbolistize,
-                  :snippet => doc[:snippet], :header => fake_header
+                  :snippet => doc[:snippet]
+      m.parse_header fake_header
+      m
     end
   end
 
@@ -483,10 +483,27 @@ EOS
     @index_mutex.synchronize { @index.search(q, :limit => 1).total_hits > 0 }
   end
 
+  ## takes a user query string and returns the list of docids for messages
+  ## that match the query.
+  ##
+  ## messages can then be loaded from the index with #build_message.
+  ##
+  ## raises a ParseError if the parsing failed.
+  def run_query query
+    qobj, opts = Redwood::Index.parse_user_query_string query
+    query = Redwood::Index.build_query opts.merge(:qobj => qobj)
+    results = @index.search query, :limit => (opts[:limit] || :all)
+    results.hits.map { |hit| hit.doc }
+  end
+
 protected
 
-  ## do any specialized parsing
-  ## returns nil and flashes error message if parsing failed
+  class ParseError < StandardError; end
+
+  ## parse a query string from the user. returns a query object and a set of
+  ## extra flags; both of these are meant to be passed to #build_query.
+  ##
+  ## raises a ParseError if something went wrong.
   def parse_user_query_string s
     extraopts = {}
 
@@ -548,11 +565,9 @@ protected
     end
 
     if $have_chronic
-      chronic_failure = false
       subs = subs.gsub(/\b(before|on|in|during|after):(\((.+?)\)\B|(\S+)\b)/) do
-        break if chronic_failure
         field, datestr = $1, ($3 || $4)
-        realdate = Chronic.parse(datestr, :guess => false, :context => :none)
+        realdate = Chronic.parse datestr, :guess => false, :context => :past
         if realdate
           case field
           when "after"
@@ -566,11 +581,9 @@ protected
             "date:(<= #{sprintf "%012d", realdate.end.to_i}) date:(>= #{sprintf "%012d", realdate.begin.to_i})"
           end
         else
-          BufferManager.flash "Can't understand date #{datestr.inspect}!"
-          chronic_failure = true
+          raise ParseError, "can't understand date #{datestr.inspect}"
         end
       end
-      subs = nil if chronic_failure
     end
 
     ## limit:42 restrict the search to 42 results
@@ -580,15 +593,14 @@ protected
         extraopts[:limit] = lim.to_i
         ''
       else
-        BufferManager.flash "Can't understand limit #{lim.inspect}!"
-        subs = nil
+        raise ParseError, "non-numeric limit #{lim.inspect}"
       end
     end
     
-    if subs
+    begin
       [@qparser.parse(subs), extraopts]
-    else
-      nil
+    rescue Ferret::QueryParser::QueryParseException => e
+      raise ParseError, e.message
     end
   end