--- loncom/homework/cleanxml/xml_to_loncapa.pm	2016/01/06 16:44:32	1.5
+++ loncom/homework/cleanxml/xml_to_loncapa.pm	2016/11/10 21:53:56	1.10
@@ -1,7 +1,7 @@
 # The LearningOnline Network
 # convert_file takes a well-formed XML file content and converts it to LON-CAPA syntax.
 #
-# $Id: xml_to_loncapa.pm,v 1.5 2016/01/06 16:44:32 damieng Exp $
+# $Id: xml_to_loncapa.pm,v 1.10 2016/11/10 21:53:56 damieng Exp $
 #
 # Copyright Michigan State University Board of Trustees
 #
@@ -38,14 +38,16 @@ use warnings;
 use XML::LibXML;
 
 
-my @loncapa_block = ('parameter','location','answer','foil','image','polygon','rectangle','text','conceptgroup','itemgroup','item','label','data','function','array','unit','answergroup','functionplotresponse','functionplotruleset','functionplotelements','functionplotcustomrule','essayresponse','hintpart','formulahint','numericalhint','reactionhint','organichint','optionhint','radiobuttonhint','stringhint','customhint','mathhint','formulahintcondition','numericalhintcondition','reactionhintcondition','organichintcondition','optionhintcondition','radiobuttonhintcondition','stringhintcondition','customhintcondition','mathhintcondition','imageresponse','foilgroup','datasubmission','textfield','hiddensubmission','radiobuttonresponse','rankresponse','matchresponse','import','style','script','window','block','library','notsolved','part','postanswerdate','preduedate','problem','problemtype','randomlabel','bgimg','labelgroup','randomlist','solved','while','tex','print','web','gnuplot','curve','Task','IntroParagraph','ClosingParagraph','Question','QuestionText','Setup','Instance','InstanceText','Criteria','CriteriaText','GraderNote','languageblock','translated','lang','instructorcomment','dataresponse','togglebox','standalone','comment','drawimage','allow','displayduedate','displaytitle','responseparam','organicstructure','scriptlib','parserlib','drawoptionlist','spline','backgroundplot','plotobject','plotvector','drawvectorsum','functionplotrule','functionplotvectorrule','functionplotvectorsumrule','axis','key','xtics','ytics','title','xlabel','ylabel','hiddenline','dtm','stringresponse','optionresponse','numericalresponse','formularesponse','mathresponse','organicresponse','reactionresponse','customresponse','externalresponse', 'hint', 'hintgroup');
+# LON-CAPA block elements that cannot be found within startouttext/endouttext
+my @loncapa_block = ('parameter','location','answer','foil','image','polygon','rectangle','text','conceptgroup','itemgroup','item','label','data','function','array','unit','answergroup','functionplotresponse','functionplotruleset','functionplotelements','functionplotcustomrule','essayresponse','hintpart','formulahint','numericalhint','reactionhint','organichint','optionhint','radiobuttonhint','stringhint','customhint','mathhint','formulahintcondition','numericalhintcondition','reactionhintcondition','organichintcondition','optionhintcondition','radiobuttonhintcondition','stringhintcondition','customhintcondition','mathhintcondition','imageresponse','foilgroup','datasubmission','textfield','hiddensubmission','radiobuttonresponse','rankresponse','matchresponse','import','style','script','window','block','library','notsolved','part','postanswerdate','preduedate','problem','problemtype','randomlabel','bgimg','labelgroup','randomlist','solved','while','tex','print','web','gnuplot','curve','Task','IntroParagraph','ClosingParagraph','Question','QuestionText','Setup','Instance','InstanceText','Criteria','CriteriaText','GraderNote','languageblock','instructorcomment','dataresponse','togglebox','standalone','comment','drawimage','allow','displayduedate','displaytitle','responseparam','organicstructure','scriptlib','parserlib','drawoptionlist','spline','backgroundplot','plotobject','plotvector','drawvectorsum','functionplotrule','functionplotvectorrule','functionplotvectorsumrule','axis','key','xtics','ytics','title','xlabel','ylabel','hiddenline','dtm','stringresponse','optionresponse','numericalresponse','formularesponse','mathresponse','organicresponse','reactionresponse','customresponse','externalresponse', 'hint', 'hintgroup');
 
-my @loncapa_inline = ('display','m','lm','chem','num','parse','algebra','displayweight','displaystudentphoto'); # not textline
+# LON-CAPA elements that can be found within startouttext/endouttext:
+my @loncapa_in_text = ('display','m','lm','chem','num','parse','algebra','displayweight','displaystudentphoto','translated','lang'); # not textline
 
 # HTML elements that trigger the addition of startouttext/endouttext
-my @html_trigger = ('header','footer','aside','h1','h2','h3','h4','h5','h6','li','dd','dt','tbody','tr','caption','thead','tfoot','td','th','span','a','em','strong','b','i','sup','sub','pre','code','kbd','samp','cite','q','tt','ins','del','var','small','big','br','hr','address','blockquote','img','figure','figcaption','object','param','embed','applet','video','source','audio','map','area','canvas','form','input','select','optgroup','option','textarea','fieldset','legend','button','iframe','section','div','p','ul','ol','dl','table');
+my @html_trigger = ('header','footer','aside','h1','h2','h3','h4','h5','h6','li','dd','dt','tbody','tr','caption','thead','tfoot','td','th','span','a','em','strong','b','i','sup','sub','pre','code','kbd','samp','cite','q','tt','ins','del','var','small','big','br','hr','address','blockquote','figure','figcaption','object','param','embed','applet','video','source','audio','map','area','canvas','form','input','select','optgroup','option','textarea','fieldset','legend','button','iframe','section','div','p','ul','ol','dl','table');
 
-my @simple_data = ('polygon', 'rectangle', 'vector', 'value', 'answer', 'title', 'data', 'function', 'xlabel', 'ylabel', 'tic', 'parserlib', 'scriptlib', 'import', 'tex', 'text', 'image', 'display', 'm', 'lm', 'num', 'algebra', 'chem', 'parse', 'title', 'style', 'script', 'ins', 'del', 'label', 'option', 'textarea', 'legend' );
+my @simple_data = ('polygon', 'rectangle', 'vector', 'value', 'answer', 'title', 'data', 'function', 'xlabel', 'ylabel', 'tic', 'parserlib', 'scriptlib', 'import', 'tex', 'text', 'image', 'display', 'm', 'lm', 'num', 'algebra', 'chem', 'parse', 'title', 'style', 'script', 'ins', 'del', 'label', 'option', 'textarea', 'legend','comment');
 
 my @inline_responses = ('stringresponse','optionresponse','numericalresponse','formularesponse','mathresponse','organicresponse','reactionresponse','customresponse','externalresponse');
 
@@ -81,7 +83,7 @@ sub node_to_string {
     if (defined $parent->parentNode) {
       $grandparent_name = $parent->parentNode->nodeName;
     }
-    my @no_escape = ('m', 'script', 'display', 'parse', 'answer');
+    my @no_escape = ('m', 'script', 'style', 'display', 'parse', 'answer');
     if (string_in_array(\@no_escape, $parent_name) &&
         ($parent_name ne 'answer' ||
         (defined $grandparent_name &&
@@ -145,6 +147,11 @@ sub add_outtext {
     return;
   }
   convert_paragraphs($node);
+  if ($node->nodeName eq 'hintgroup' && !defined $node->firstChild) {
+    # empty hintgroup: colorful editor needs start/end outtext
+    add_endouttext($node, undef);
+    add_startouttext($node, $node->firstChild);
+  }
   my $next;
   my $in_outtext = 0;
   for (my $child=$node->firstChild; defined $child; $child=$next) {
@@ -178,7 +185,7 @@ sub inside_outtext {
       return 1;
     }
   }
-  if ($node->nodeType == XML_ELEMENT_NODE && string_in_array(\@loncapa_inline, $node->nodeName)) {
+  if ($node->nodeType == XML_ELEMENT_NODE && string_in_array(\@loncapa_in_text, $node->nodeName)) {
     return 1;
   }
   return 0;
@@ -255,6 +262,21 @@ sub add_endouttext {
   } else {
     $parent->appendChild($endouttext);
   }
+  # replace spaces afterwards by a \n + indentation
+  my $next = $endouttext->nextSibling;
+  if (defined $next && $next->nodeType == XML_TEXT_NODE) {
+    my $v = $next->nodeValue;
+    if ($v =~ /^ /) {
+      $v =~ s/^ +//;
+      if ($parent->firstChild->nodeType == XML_TEXT_NODE &&
+          $parent->firstChild->nodeValue =~ /^\n +$/) {
+        $v = $parent->firstChild->nodeValue.$v;
+      } else {
+        $v = "\n".$v;
+      }
+      $next->setData($v);
+    }
+  }
 }
 
 # Convert paragraph children when one contains an inline response into content + <br>
@@ -289,6 +311,9 @@ sub convert_paragraphs {
           # we only add a br if there is something after
           my $br = $doc->createElement('br');
           $parent->insertBefore($br, $next);
+          # add another br to make up for the p margin
+          $br = $doc->createElement('br');
+          $parent->insertBefore($br, $next);
         }
       }
     }