Changeset 575:f0e5e9c6737f in documentViewer for MpiwgXmlTextServer.py

Timestamp:

Oct 16, 2012, 5:46:53 PM (12 years ago)

Author:

casties

Branch:

default

Message:

new w-tag solution with css.
(processWTags doesn't work)

File:

• MpiwgXmlTextServer.py (modified) (5 diffs)

MpiwgXmlTextServer.py

@@ -205 +205 @@
                       'page': pn}
         
-        if 'characterNormalization' in pageinfo:
-            cn = pageinfo['characterNormalization']
-            # TODO: change values in form
-            if cn == 'regPlusNorm':
-                cn = 'norm'
-                
-            textParams['normalization'] = cn
-        
+        normMode = pageinfo.get('characterNormalization', 'reg')
+        # TODO: change values in form
+        if normMode == 'regPlusNorm':
+            normMode = 'norm'
+                        
         if not mode:
             # default is dict
@@ -250 +247 @@
             textParams['mode'] = 'untokenized'
             textParams['outputFormat'] = 'xmlDisplay'
-            textParams['normalization'] = 'orig'
+            textParams['normMode'] = 'orig'
         elif 'gis' in modes:
             #FIXME!
@@ -256 +253 @@
         else:
             # text is default mode
-            textmode = 'text'
+            textmode = 'plain'
             textParams['mode'] = 'untokenized'
             textParams['outputFormat'] = 'html'
@@ -269 +266 @@
         
         # plain text or text-with-links mode
-        if textmode == "text" or textmode == "dict":
+        if textmode == "plain" or textmode == "dict":
             # the text is in div@class=text
             pagediv = dom.find(".//div[@class='text']")
             logging.debug("pagediv: %s"%repr(pagediv))
             if pagediv is not None:
+                # add textmode and normMode classes
+                pagediv.set('class', 'text %s %s'%(textmode, normMode))
+                #self._processWTags(textmode, normMode, pagediv)
                 #self._processPbTag(pagediv, pageinfo)
                 self._processFigures(pagediv, docinfo)
@@ -343 +343 @@
         return None
 
+    def _processWTags(self, textMode, normMode, pagediv):
+        """selects the necessary information from w-spans and removes the rest from pagediv"""
+        logging.debug("processWTags(textMode=%s,norm=%s,pagediv"%(repr(textMode),repr(normMode)))
+        wtags = pagediv.findall(".//span[@class='w']")
+        for wtag in wtags:
+            text = None
+            attr = None
+            if textMode == 'dict':
+                # take a-tag and matching child
+                attr = wtag.find('a').items()
+                text = wtag.find("a/span[@class='%s']"%normMode).text
+            else:
+                # take matching child
+                text = wtag.find("span[@class='nodictionary %s']"%normMode).text
+                
+            if text:
+                # replace wtag by new content
+                logging.debug("new w-tag attr=%s text=%s"%(attr,text))
+                wtag.clear()
+                    
+                if attr:
+                    # make dictionary link
+                    wtag.tag = 'a'
+                    wtag.attrib.update(dict(attr))
+                    
+                # text content
+                wtag.text = text
+                
+        return pagediv
+        
     def _processPbTag(self, pagediv, pageinfo):
         """extracts information from pb-tag and removes it from pagediv"""