Support explicit HTML markup in fields when the markup="html" attribute is present

src/common/cstr.h

@@ -56,7 +56,8 @@ DEF_CSTR(null, "");
 DEF_CSTR(plus, "+");
 DEF_CSTR(textplain, "text/plain");
 DEF_CSTR(url, "url");
-
+// Marker for HTML format fields
+DEF_CSTR(fldhtm, "\007");
 
 // Values used as keys inside Dijon::Filter::metaData[]. This structure is 
 // used to store all data generated by format-translating filters. It is

src/internfile/myhtmlparse.cpp

@@ -360,9 +360,7 @@ MyHtmlParser::opening_tag(const string &tag)
 		    if (get_parameter("name", name)) {
 			lowercase_term(name);
 			if (name == "date") {
-			    // Yes this doesnt exist. It's output by filters
-			    // And the format isn't even standard http/html
-			    // FIXME
+			    // Specific to Recoll filters.
 			    decode_entities(content);
 			    struct tm tm;
 			    if (strptime(content.c_str(), 
@@ -376,10 +374,22 @@ MyHtmlParser::opening_tag(const string &tag)
 			    }
 			} else if (name == "robots") {
 			} else {
+			    string markup;
+			    bool ishtml = false;
+			    if (get_parameter("markup", markup)) {
+				if (!stringlowercmp("html", markup)) {
+				    ishtml = true;
+				}
+			    }
 			    if (!meta[name].empty())
 				meta[name] += ' ';
 			    decode_entities(content);
 			    meta[name] += content;
+			    if (ishtml && 
+				meta[name].compare(0, cstr_fldhtm.size(), 
+						   cstr_fldhtm)) {
+				meta[name].insert(0, cstr_fldhtm);
+			    }
 			}
 		    } 
 		    string hdr;
@@ -417,8 +427,7 @@ MyHtmlParser::opening_tag(const string &tag)
 		    }
 		}
 		break;
-	    }
-	    if (tag == "marquee" || tag == "menu" || tag == "multicol")
+	    } else if (tag == "marquee" || tag == "menu" || tag == "multicol")
 		pending_space = true;
 	    break;
 	case 'o':
@@ -441,12 +450,11 @@ MyHtmlParser::opening_tag(const string &tag)
 	    if (tag == "style") {
 		in_style_tag = true;
 		break;
-	    }
-	    if (tag == "script") {
+	    } else if (tag == "script") {
 		in_script_tag = true;
 		break;
-	    }
-	    if (tag == "select") pending_space = true;
+	    } else if (tag == "select") 
+		pending_space = true;
 	    break;
 	case 't':
 	    if (tag == "table" || tag == "td" || tag == "textarea" ||

src/query/reslistpager.cpp

@@ -110,6 +110,14 @@ void ResListPager::resultPageNext()
     m_resultsInCurrentPage = pagelen;
     m_respage = npage;
 }
+static string maybeEscapeHtml(const string& fld)
+{
+    if (fld.compare(0, cstr_fldhtm.size(), cstr_fldhtm))
+	return escapeHtml(fld);
+    else
+	return fld.substr(cstr_fldhtm.size());
+}
+
 
 void ResListPager::resultPageFor(int docnum)
 {
@@ -263,21 +271,21 @@ void ResListPager::displayDoc(RclConfig *config, int i, Rcl::Doc& doc,
     subs["I"] = iconurl;
     subs["i"] = doc.ipath;
     subs["K"] = !doc.meta[Rcl::Doc::keykw].empty() ? 
-	string("[") + escapeHtml(doc.meta[Rcl::Doc::keykw]) + "]" : "";
+	string("[") + maybeEscapeHtml(doc.meta[Rcl::Doc::keykw]) + "]" : "";
     subs["L"] = linksbuf.str();
     subs["N"] = numbuf;
     subs["M"] = doc.mimetype;
     subs["R"] = doc.meta[Rcl::Doc::keyrr];
     subs["S"] = sizebuf;
-    subs["T"] = escapeHtml(titleOrFilename);
-    subs["t"] = escapeHtml(doc.meta[Rcl::Doc::keytt]);
+    subs["T"] = maybeEscapeHtml(titleOrFilename);
+    subs["t"] = maybeEscapeHtml(doc.meta[Rcl::Doc::keytt]);
     subs["U"] = url;
 
     // Let %(xx) access all metadata. HTML-neuter everything:
     for (map<string,string>::iterator it = doc.meta.begin(); 
 	 it != doc.meta.end(); it++) {
 	if (!it->first.empty()) 
-	    subs[it->first] = escapeHtml(it->second);
+	    subs[it->first] = maybeEscapeHtml(it->second);
     }
 
     string formatted;

website/index.html.en

@@ -84,6 +84,22 @@
       <h2>News</h2>
       <div class="news">
       <ul>
+        <li>2012-10-25: a problem with a simple workaround has caused
+          several reported <span class="important">recollindex
+          crashes</span> recently. If you store and index
+          Mozilla/Thunderbird email out of the standard location
+          (~/.thunderbird), you should add the following at the end of
+          your configuration file (e.g.:
+          ~/.recoll/recoll.conf): <pre><tt>
+              [/path/to/my/mozilla/mail]
+              mhmboxquirks = tbird
+          </tt></pre> Adjust the path to your local value of course...
+          Without this hint, recollindex has trouble finding the
+          message delimiters inside the folder files, and will
+          possibly use all the computer's memory and crash. Apart from
+          crashes, which only occur for very big folders, this also
+          causes incorrect mail indexing.
+        </li>
         <li>2012-10-19: the source for <a href="recoll-1.18.001.tar.gz">
             recoll 1.18.001</a> is available, and this is a call to
             volunteers to test it. There are binary

website/index.html.fr

@@ -100,6 +100,25 @@
       <h2>Nouvelles: </h2>
       <ul>
 
+        <li>2012-10-25: Un problème avec une solution simple peut provoquer
+          des <span class="important">plantages de
+          recollindex</span>. 
+          Si vous indexez des messages mail Mozilla/Thunderbird
+          ailleurs qu'à l'endroit standard (~/.thunderbird), vous
+          devriez ajouter les lignes qui suivent à la fin de votre
+          fichier de configuration (~/.recoll/recoll.conf):
+          <pre><tt>
+              [/path/to/my/mozilla/mail]
+              mhmboxquirks = tbird
+          </tt></pre> Changez le chemin d'accès pour le votre bien
+          sûr.  Sans cette indication, recollindex a des difficultés à
+          déterminer les limites de message dans les fichiers mailbox,
+          et peut arriver à utiliser toute la mémoire de la machine,
+          et à se planter. Dans les cas moins graves (avec des
+          fichiers de taille "raisonnable"), cela provoque aussi une
+          indexation incorrecte des messages.
+        </li>
+
         <li>2012-10-16: <a href="filters/filters.html">un nouveau filtre
             pour les documents EPUB</a>.</li> 
         <li>2012-05-24: Sortie de la