pdf: add and document MetaFixer::wrapup() method

src/doc/user/usermanual.html

@@ -20,8 +20,8 @@ alink="#0000FF">
     <div class="titlepage">
       <div>
         <div>
-          <h1 class="title"><a name="idp35245072" id=
+          <h1 class="title"><a name="idp56557776" id=
-          "idp35245072"></a>Recoll user manual</h1>
+          "idp56557776"></a>Recoll user manual</h1>
         </div>
 
         <div>
@@ -109,13 +109,13 @@ alink="#0000FF">
                 multiple indexes</a></span></dt>
 
                 <dt><span class="sect2">2.1.3. <a href=
-                "#idp40818624">Document types</a></span></dt>
+                "#idp62130176">Document types</a></span></dt>
 
                 <dt><span class="sect2">2.1.4. <a href=
-                "#idp40843200">Indexing failures</a></span></dt>
+                "#idp62154272">Indexing failures</a></span></dt>
 
                 <dt><span class="sect2">2.1.5. <a href=
-                "#idp40850208">Recovery</a></span></dt>
+                "#idp62161280">Recovery</a></span></dt>
               </dl>
             </dd>
 
@@ -1017,8 +1017,8 @@ alink="#0000FF">
           <div class="titlepage">
             <div>
               <div>
-                <h3 class="title"><a name="idp40818624" id=
+                <h3 class="title"><a name="idp62130176" id=
-                "idp40818624"></a>2.1.3.&nbsp;Document types</h3>
+                "idp62130176"></a>2.1.3.&nbsp;Document types</h3>
               </div>
             </div>
           </div>
@@ -1131,8 +1131,8 @@ indexedmimetypes = application/pdf
           <div class="titlepage">
             <div>
               <div>
-                <h3 class="title"><a name="idp40843200" id=
+                <h3 class="title"><a name="idp62154272" id=
-                "idp40843200"></a>2.1.4.&nbsp;Indexing
+                "idp62154272"></a>2.1.4.&nbsp;Indexing
                 failures</h3>
               </div>
             </div>
@@ -1172,8 +1172,8 @@ indexedmimetypes = application/pdf
           <div class="titlepage">
             <div>
               <div>
-                <h3 class="title"><a name="idp40850208" id=
+                <h3 class="title"><a name="idp62161280" id=
-                "idp40850208"></a>2.1.5.&nbsp;Recovery</h3>
+                "idp62161280"></a>2.1.5.&nbsp;Recovery</h3>
               </div>
             </div>
           </div>
@@ -2042,8 +2042,20 @@ class MetaFixer(object):
             pass
     
         return txt
+    def wrapup(self, metaheaders):
+        pass
         
 </pre>
+
+          <p>If the 'metafix()' method is defined, it is called for
+          each metadata field. A new MetaFixer object is created
+          for each PDF document (so the object can keep state for,
+          for example, eliminating duplicate values). If the
+          'wrapup()' method is defined, it is called at the end of
+          XMP fields processing with the whole metadata as
+          parameter, as an array of '(nm, val)' pairs, allowing an
+          alternate approach for editing or adding/deleting
+          fields.</p>
         </div>
 
         <div class="sect2">

src/doc/user/usermanual.xml

@@ -1174,8 +1174,17 @@ class MetaFixer(object):
             pass
     
         return txt
+    def wrapup(self, metaheaders):
+        pass
         </programlisting>
 
+        <para>If the 'metafix()' method is defined, it is called for each
+        metadata field. A new MetaFixer object is created for each PDF
+        document (so the object can keep state for, for example,
+        eliminating duplicate values). If the 'wrapup()' method is defined, it
+        is called at the end of XMP fields processing with the whole
+        metadata as parameter, as an array of '(nm, val)' pairs, allowing
+        an alternate approach for editing or adding/deleting fields.</para>
         
         <!-- <para> There is a <ulink url="&WIKI;PDFXMP.wiki">complete example of XMP
         tags setup</ulink>, including a  nice result list paragraph format in the 

src/filters/rclpdf.py

@@ -400,23 +400,20 @@ class PDFExtractor:
 
         emf = EMF.MetaFixer() if EMF else None
 
+        # Execute pdfinfo and extract the XML packet
         all = subprocess.check_output([self.pdfinfo, "-meta", self.filename])
-
-        # Extract the XML packet
         res = self.re_xmlpacket.search(all)
-        xml = ''
+        xml = res.group(1) if res else ''
-        if res:
-            xml = res.group(1)
         #self.em.rclog("extrameta: XML: [%s]" % xml)
         if not xml:
             return html
 
+        # Process the XML data
+        root = ET.fromstring(xml)
+        # Sometimes the root tag is <x:xmpmeta>, sometimes <rdf:RDF>
         # The namespace thing is a drag. Can't do it from the top. See
         # the stackoverflow ref above. Maybe we'd be better off just
         # walking the full tree and building the namespaces dict.
-        root = ET.fromstring(xml)
-
-        # Sometimes the root tag is <x:xmpmeta>, sometimes <rdf:RDF>
         if root.tag.endswith('RDF'):
             rdf = root
         else:
@@ -441,13 +438,21 @@ class PDFExtractor:
                 if elt is not None:
                     text = self._xmltreetext(elt).encode('UTF-8')
                     if emf:
-                        text = emf.metafix(metanm, text)
+                        try:
+                            text = emf.metafix(metanm, text)
+                        except:
+                            pass
                     # Should we set empty values ?
                     if text:
                         # Can't use setfield as it only works for
                         # text/plain output at the moment.
                         metaheaders.append((rclnm, text))
         if metaheaders:
+            if emf:
+                try:
+                    emf.wrapup(metaheaders)
+                except:
+                    pass
             return self._injectmeta(html, metaheaders)
         else:
             return html