a lot of fixes and additions, most notably: also sending json

4 files changed, 69 insertions, 17 deletions

diff --git a/js/lfpe.js b/js/lfpe.js
index e2b0f42..edfae9b 100644
--- a/js/lfpe.js
+++ b/js/lfpe.js
@@ -162,23 +162,31 @@ function Next()
 
   // post edit
   var post_edit = '';
+  var send_data = new Object();
 
   // extract data from interfaces
   if (ui_type == 'g') {
-    post_edit = trim(JSON.parse(DE_extract_data())["target"].join(" "))
+    send_data = JSON.parse(DE_extract_data());
+    post_edit = trim(send_data["target"].join(" "));
+    send_data["post_edit"] = post_edit;
   } else {
     post_edit = trim(target_textarea.value);
+    send_data["post_edit"] = post_edit;
   }
 
   // send data
   // ???
   if (oov_correct.value=="false" && post_edit != "") {
+      send_data["duration"] = Timer.get();
+      send_data["source_value"] = source.value;
       // compose request
-      next_url += "&example="+encodeURIComponent(source.value)+"%20%7C%7C%7C%20"+encodeURIComponent(post_edit)+"&duration="+Timer.get();
+      //next_url += "&example="+encodeURIComponent(source.value)+"%20%7C%7C%7C%20"+encodeURIComponent(post_edit)+"&duration="+Timer.get();
       // no change?
       if (post_edit == last_post_edit.value) {
-        next_url += "&nochange=1";
+        //next_url += "&nochange=1";
+        send_data["nochange"] = true;
       }
+      next_url += "&example="+encodeURIComponent(JSON.stringify(send_data));
       // update document overview
       document.getElementById("seg_"+(current_seg_id.value)+"_t").innerHTML=post_edit;
   // OOV correction mode
diff --git a/server.rb b/server.rb
index 6b81b36..b0da33a 100755
--- a/server.rb
+++ b/server.rb
@@ -174,11 +174,16 @@ get '/next' do      # (receive post-edit, update models), send next translation
   # 5d. actual update
   # 6. update database
   if params[:example]
+    logmsg :server, params[:example]
+    rcv_obj = JSON.parse params[:example]
     # 0. save raw post-edit
-    source, reference = params[:example].strip.split(" ||| ")
+    #source, reference = params[:example].strip.split(" ||| ")
+    source = rcv_obj["source_value"]
+    reference = rcv_obj["target"].join " "
     reference = cleanstr(reference)
+    $db['feedback'] << params[:example]
     $db['post_edits_raw'] << reference.strip
-    $db['durations'] << params['duration'].to_i
+    $db['durations'] << rcv_obj['duration'].to_i
     # 1. tokenize
       reference = send_recv :tokenizer, reference
     # 2. truecase
@@ -187,7 +192,7 @@ get '/next' do      # (receive post-edit, update models), send next translation
       logmsg :db, "saving processed post-edit"
       $db['post_edits'] << reference.strip
     nochange = false
-    if params[:nochange]
+    if rcv_obj[:nochange]
       logmsg :server, "no change -> no updates!"
       nochange = true
     end
@@ -210,8 +215,11 @@ get '/next' do      # (receive post-edit, update models), send next translation
       send_recv :extractor, "default_context ||| #{source} ||| #{reference} ||| #{a}"
     # 6. update database
       logmsg :db, "updating database"
+      $db['updated'] << true
+    else
+      $db['updated'] << false
     end
-      update_database
+    update_database
   end
   source     = $db['source_segments'][$db['progress']]
   raw_source = $db['raw_source_segments'][$db['progress']]
@@ -284,7 +292,8 @@ get '/next' do      # (receive post-edit, update models), send next translation
     end
     # 3. translation
     msg = "act:translate ||| <seg grammar=\"#{grammar}\"> #{source} </seg>"
-    obj_str = proc_deriv(send_recv(:dtrain, msg))
+    deriv_s = send_recv(:dtrain, msg)
+    obj_str = proc_deriv(deriv_s)
     obj = JSON.parse obj_str
     obj["transl"] = obj["target_groups"].join " "
     # 4. detokenizer
@@ -305,8 +314,10 @@ get '/next' do      # (receive post-edit, update models), send next translation
       obj["source_groups"][j][0]=prev if j > 0
     }
     # save
-    $db["mt_raw"] = obj["transl"]
-    $db["mt"] = obj["transl_detok"]
+    $db["derivations"] << deriv_s
+    $db["derivations_proc"] << obj_str
+    $db["mt_raw"] << obj["transl"]
+    $db["mt"] << obj["transl_detok"]
     # 5. reply
     $last_reply = obj.to_json
     $lock = false
@@ -367,8 +378,15 @@ get '/reset' do                                         # reset current session
   $db = JSON.parse ReadFile.read DB_FILE
   $db['post_edits'].clear
   $db['post_edits_raw'].clear
+  $db['mt'].clear
+  $db['mt_raw'].clear
+  $db['updated'].clear
+  $db['durations'].clear
+  $db['derivations'].clear
+  $db['derivations_proc'].clear
+  $db['feedback'].clear
+  $db['progress'] = -1
   update_database
-  $db['progress'] = 0
   $confirmed = true
   $last_reply = nil
 
diff --git a/util/wrapper.rb b/util/wrapper.rb
index b760333..d0e6ca7 100755
--- a/util/wrapper.rb
+++ b/util/wrapper.rb
@@ -22,7 +22,7 @@ if conf[:action] == "detokenize"
     STDERR.write "[detokenizer] No language given, exiting!\n"; exit
   end
 elsif conf[:action] == "tokenize"
-  cmd = "#{conf[:ext]}/tokenizer-no-escape.perl -q -b -a -l #{conf[:lang]}"
+  cmd = "#{conf[:ext]}/tokenizer-no-escape.perl -q -b -l #{conf[:lang]}"
   if !conf[:lang]
     STDERR.write "[tokenizer] No language given, exiting!\n"; exit
   end
diff --git a/views/debug.haml b/views/debug.haml
index 7e8b164..5b7ad20 100644
--- a/views/debug.haml
+++ b/views/debug.haml
@@ -5,7 +5,7 @@
     %title debug view (session ##{session_key})
   %link(rel="stylesheet" type="text/css" href="debug.css")
   %script{:src =>"http://ajax.googleapis.com/ajax/libs/jquery/1.11.2/jquery.min.js", :charset=>"utf-8"}
-  %script{:src => "http://coltrane.cl.uni-heidelberg.de/lfpe/js/debug.js"}
+  %script{:src => "http://postedit.cl.uni-heidelberg.de/js/debug.js"}
   %body
     %h1 debug view
     %h2 session ##{session_key}
@@ -36,27 +36,53 @@
     %table
       %tr
         %td.noborder
+          %strong progress:
+        %td.left #{[0,data2["progress"]-1].max}
+      %tr
+        %td.noborder
           %strong source:
-        %td.left #{data["source"]}
+        %td.left #{data2["source_segments"][[0,data2["progress"]-1].max]}
+      %tr
+        %td.noborder
+          %strong source (original):
+        %td.left #{data2["raw_source_segments"][[0,data2["progress"]-1].max]}
       %tr
         %td.noborder
           %strong post-edit:
-        %td.left #{data["target"]}
+        %td.left #{data2["post_edits_raw"][data2["progress"]-1]}
+      %tr
+        %td.noborder
+          %strong post-edit (processed):
+        %td.left #{data2["post_edits"][data2["progress"]-1]}
       %tr
         %td.noborder
           %strong original mt:
-        %td.left #{data["1best"]}
+        %td.left #{data2["mt_raw"][data2["progress"]-1]}
+      %tr
+        %td.noborder
+          %strong shown mt:
+        %td.left #{data2["mt"][data2["progress"]-1]}
       %tr
         %td.noborder
           %strong best match (bleu=#{data["best_match_score"]}):
         %td.left #{data["best_match"]}
+    %h2 derivation
+    %pre #{data2["derivations"][data2["progress"]-1]}
+    %p
+      %strong processed
+    - if data2["derivations_proc"][data2["progress"]-1]
+      %pre #{JSON.pretty_generate(JSON.parse(data2["derivations_proc"][data2["progress"]-1]))}
+    %h2 manual update
+    - if data2["feedback"][data2["progress"]-1]
+      %pre #{JSON.pretty_generate(JSON.parse(data2["feedback"][data2["progress"]-1]))}
     %h2 meta
     %p <strong>k:</strong> #{data["samples_size"]}
     %p <strong>number of updates:</strong> #{data["num_up"]}
     %p <strong>updated features:</strong> #{data["updated_features"]}
     %p <strong>learning rate:</strong> #{data["learning_rate"]}
     %p <strong>learning rate (sparse):</strong> #{data["learning_rate_sparse"]}
-    %p <strong>duration:</strong> #{data2["durations"][[data2["progress"].to_i-1].max]}ms
+    %p <strong>duration:</strong> #{data2["durations"][data2["progress"].to_i-1]}ms
+    %p <strong>updated:</strong> #{data2["updated"][data2["progress"].to_i-1]}
     %h2
       additional rules (forced rules)
     %pre #{additional_rules.join("\n")}